{ "info": { "_postman_id": "cc78fcf9-8fc2-4d97-bf1a-54b831ef012b", "name": "SLNG Voice Agents Account Deepgram Nova 3 API", "description": "Public API for managing Voice Agents, dispatching outbound calls, and creating web (non-telephony) sessions.\n\nBase URL: `https://api.agents.slng.ai`\n\n\nContact Support:\n Name: SLNG Support\n Email: support@slng.ai", "schema": "https://schema.getpostman.com/json/collection/v2.1.0/collection.json", "createdAt": "2026-07-28T02:55:30.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "lastUpdatedBy": "35240", "uid": "35240-cc78fcf9-8fc2-4d97-bf1a-54b831ef012b" }, "item": [ { "name": "v1", "item": [ { "name": "stt", "item": [ { "name": "slng", "item": [ { "name": "deepgram", "item": [ { "name": "nova:3-en", "item": [ { "name": "Nova 3 (English)", "id": "5f4d07d4-00fd-4106-9b45-9d8d52bf7e14", "protocolProfileBehavior": { "disableBodyPruning": true }, "request": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "australia-southeast1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file", "value": null }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,ssn", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported English language code. (This can only be one of en,en-au,en-us,en-nz,en-gb,en-in)", "key": "language", "value": "en", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-en", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-en" ] }, "description": "Transcribe English audio using SLNG-hosted Deepgram Nova 3." }, "response": [ { "id": "583e004b-3750-4ccb-be45-c8fa9cebaf6e", "name": "Transcription successful.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "australia-southeast1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,ssn", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported English language code. (This can only be one of en,en-au,en-us,en-nz,en-gb,en-in)", "key": "language", "value": "en", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-en", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-en" ] } }, "status": "OK", "code": 200, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"results\": {\n \"channels\": [\n {\n \"alternatives\": [\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n },\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n }\n ],\n \"detected_language\": \"\"\n },\n {\n \"alternatives\": [\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n },\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n }\n ],\n \"detected_language\": \"\"\n }\n ]\n },\n \"metadata\": {\n \"request_id\": \"\",\n \"model\": \"\"\n }\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-583e004b-3750-4ccb-be45-c8fa9cebaf6e" }, { "id": "4aae0f80-7799-4e01-8c4f-6b31237200bc", "name": "Bad request - invalid parameters provided.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "australia-southeast1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,ssn", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported English language code. (This can only be one of en,en-au,en-us,en-nz,en-gb,en-in)", "key": "language", "value": "en", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-en", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-en" ] } }, "status": "Bad Request", "code": 400, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-4aae0f80-7799-4e01-8c4f-6b31237200bc" }, { "id": "75b6aac7-777e-4ff1-8aa6-3d350a9aed34", "name": "Invalid or missing API key.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "australia-southeast1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,ssn", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported English language code. (This can only be one of en,en-au,en-us,en-nz,en-gb,en-in)", "key": "language", "value": "en", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-en", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-en" ] } }, "status": "Unauthorized", "code": 401, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-75b6aac7-777e-4ff1-8aa6-3d350a9aed34" }, { "id": "cf4efdb5-07c9-4f7d-acba-db68ac66aa0e", "name": "Audio file exceeds size limit.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "australia-southeast1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,ssn", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported English language code. (This can only be one of en,en-au,en-us,en-nz,en-gb,en-in)", "key": "language", "value": "en", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-en", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-en" ] } }, "status": "Request Entity Too Large", "code": 413, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-cf4efdb5-07c9-4f7d-acba-db68ac66aa0e" }, { "id": "f27cce1b-116d-442f-8fbe-09aaf8b24b2f", "name": "Internal server error from the provider.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "australia-southeast1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,ssn", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported English language code. (This can only be one of en,en-au,en-us,en-nz,en-gb,en-in)", "key": "language", "value": "en", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-en", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-en" ] } }, "status": "Internal Server Error", "code": 500, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-f27cce1b-116d-442f-8fbe-09aaf8b24b2f" }, { "id": "aaadddb2-3704-49d0-b942-986c44937525", "name": "Service unavailable.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "australia-southeast1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,ssn", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported English language code. (This can only be one of en,en-au,en-us,en-nz,en-gb,en-in)", "key": "language", "value": "en", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-en", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-en" ] } }, "status": "Service Unavailable", "code": 503, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-aaadddb2-3704-49d0-b942-986c44937525" } ], "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-5f4d07d4-00fd-4106-9b45-9d8d52bf7e14" } ], "id": "315963da-d8ad-4dff-9238-3659a93a6478", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-315963da-d8ad-4dff-9238-3659a93a6478" }, { "name": "nova:3-es", "item": [ { "name": "Nova 3 (Spanish)", "id": "b74f508a-a44e-4418-b5e5-ad489caece82", "protocolProfileBehavior": { "disableBodyPruning": true }, "request": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "us-east-1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file", "value": null }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "pci,pci", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported Spanish language code. (This can only be one of es,es-us,es-419,es-ar,es-mx,es-es)", "key": "language", "value": "es-mx", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-es", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-es" ] }, "description": "Transcribe Spanish audio using SLNG-hosted Deepgram Nova 3." }, "response": [ { "id": "c0e1302e-3c42-4b06-8e46-17f002f9d34f", "name": "Transcription successful.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "us-east-1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "pci,pci", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported Spanish language code. (This can only be one of es,es-us,es-419,es-ar,es-mx,es-es)", "key": "language", "value": "es-mx", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-es", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-es" ] } }, "status": "OK", "code": 200, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"results\": {\n \"channels\": [\n {\n \"alternatives\": [\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n },\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n }\n ],\n \"detected_language\": \"\"\n },\n {\n \"alternatives\": [\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n },\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n }\n ],\n \"detected_language\": \"\"\n }\n ]\n },\n \"metadata\": {\n \"request_id\": \"\",\n \"model\": \"\"\n }\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-c0e1302e-3c42-4b06-8e46-17f002f9d34f" }, { "id": "39ace970-697b-448f-9503-08d37cd79d72", "name": "Bad request - invalid parameters provided.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "us-east-1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "pci,pci", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported Spanish language code. (This can only be one of es,es-us,es-419,es-ar,es-mx,es-es)", "key": "language", "value": "es-mx", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-es", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-es" ] } }, "status": "Bad Request", "code": 400, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-39ace970-697b-448f-9503-08d37cd79d72" }, { "id": "d5c31512-54df-4951-9945-0f46b8ed428e", "name": "Invalid or missing API key.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "us-east-1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "pci,pci", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported Spanish language code. (This can only be one of es,es-us,es-419,es-ar,es-mx,es-es)", "key": "language", "value": "es-mx", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-es", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-es" ] } }, "status": "Unauthorized", "code": 401, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-d5c31512-54df-4951-9945-0f46b8ed428e" }, { "id": "dec1e8d7-d8ef-47bb-bfc2-6e3320f00216", "name": "Audio file exceeds size limit.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "us-east-1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "pci,pci", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported Spanish language code. (This can only be one of es,es-us,es-419,es-ar,es-mx,es-es)", "key": "language", "value": "es-mx", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-es", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-es" ] } }, "status": "Request Entity Too Large", "code": 413, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-dec1e8d7-d8ef-47bb-bfc2-6e3320f00216" }, { "id": "33c182d6-4397-45b7-a3ae-2405f81c614f", "name": "Internal server error from the provider.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "us-east-1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "pci,pci", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported Spanish language code. (This can only be one of es,es-us,es-419,es-ar,es-mx,es-es)", "key": "language", "value": "es-mx", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-es", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-es" ] } }, "status": "Internal Server Error", "code": 500, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-33c182d6-4397-45b7-a3ae-2405f81c614f" }, { "id": "9eae29af-793c-4077-8981-c848fb7e7a12", "name": "Service unavailable.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "us-east-1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "pci,pci", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported Spanish language code. (This can only be one of es,es-us,es-419,es-ar,es-mx,es-es)", "key": "language", "value": "es-mx", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-es", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-es" ] } }, "status": "Service Unavailable", "code": 503, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-9eae29af-793c-4077-8981-c848fb7e7a12" } ], "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-b74f508a-a44e-4418-b5e5-ad489caece82" } ], "id": "053c5e72-1589-45ee-9cd0-4ec862f3cfd9", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-053c5e72-1589-45ee-9cd0-4ec862f3cfd9" }, { "name": "nova:3-hi", "item": [ { "name": "Nova 3 (Hindi)", "id": "83dc8d00-d097-43d2-a127-fb8dc617feb2", "protocolProfileBehavior": { "disableBodyPruning": true }, "request": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "asia-south1" }, { "description": "Target world part override. Auto-selected if not provided.", "key": "X-World-Part-Override", "value": "ap" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file", "value": null }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,numbers", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported language codes for the Hindi variant. (This can only be one of hi,en)", "key": "language", "value": "hi", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-hi", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-hi" ] }, "description": "Transcribe Hindi audio using SLNG-hosted Deepgram Nova 3." }, "response": [ { "id": "c3d7b8cc-3141-4bb0-89c8-2add5044270b", "name": "Transcription successful.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "asia-south1" }, { "description": "Target world part override. Auto-selected if not provided.", "key": "X-World-Part-Override", "value": "ap" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,numbers", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported language codes for the Hindi variant. (This can only be one of hi,en)", "key": "language", "value": "hi", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-hi", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-hi" ] } }, "status": "OK", "code": 200, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"results\": {\n \"channels\": [\n {\n \"alternatives\": [\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n },\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n }\n ],\n \"detected_language\": \"\"\n },\n {\n \"alternatives\": [\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n },\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n }\n ],\n \"detected_language\": \"\"\n }\n ]\n },\n \"metadata\": {\n \"request_id\": \"\",\n \"model\": \"\"\n }\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-c3d7b8cc-3141-4bb0-89c8-2add5044270b" }, { "id": "9e5d8742-78f7-4e93-b2f0-b8b1d9d97350", "name": "Bad request - invalid parameters provided.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "asia-south1" }, { "description": "Target world part override. Auto-selected if not provided.", "key": "X-World-Part-Override", "value": "ap" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,numbers", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported language codes for the Hindi variant. (This can only be one of hi,en)", "key": "language", "value": "hi", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-hi", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-hi" ] } }, "status": "Bad Request", "code": 400, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-9e5d8742-78f7-4e93-b2f0-b8b1d9d97350" }, { "id": "ef2627e1-c244-4dda-8618-a48b204a7b50", "name": "Invalid or missing API key.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "asia-south1" }, { "description": "Target world part override. Auto-selected if not provided.", "key": "X-World-Part-Override", "value": "ap" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,numbers", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported language codes for the Hindi variant. (This can only be one of hi,en)", "key": "language", "value": "hi", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-hi", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-hi" ] } }, "status": "Unauthorized", "code": 401, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-ef2627e1-c244-4dda-8618-a48b204a7b50" }, { "id": "c69c924a-e432-4be0-9c7b-06ca6714cd44", "name": "Audio file exceeds size limit.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "asia-south1" }, { "description": "Target world part override. Auto-selected if not provided.", "key": "X-World-Part-Override", "value": "ap" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,numbers", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported language codes for the Hindi variant. (This can only be one of hi,en)", "key": "language", "value": "hi", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-hi", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-hi" ] } }, "status": "Request Entity Too Large", "code": 413, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-c69c924a-e432-4be0-9c7b-06ca6714cd44" }, { "id": "e27797eb-6eb4-4f14-9ad2-fdcb90f1d48c", "name": "Internal server error from the provider.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "asia-south1" }, { "description": "Target world part override. Auto-selected if not provided.", "key": "X-World-Part-Override", "value": "ap" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,numbers", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported language codes for the Hindi variant. (This can only be one of hi,en)", "key": "language", "value": "hi", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-hi", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-hi" ] } }, "status": "Internal Server Error", "code": 500, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-e27797eb-6eb4-4f14-9ad2-fdcb90f1d48c" }, { "id": "f50b8d1c-1ce3-41ab-b512-6f8feb4594fc", "name": "Service unavailable.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "asia-south1" }, { "description": "Target world part override. Auto-selected if not provided.", "key": "X-World-Part-Override", "value": "ap" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,numbers", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported language codes for the Hindi variant. (This can only be one of hi,en)", "key": "language", "value": "hi", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-hi", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-hi" ] } }, "status": "Service Unavailable", "code": 503, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-f50b8d1c-1ce3-41ab-b512-6f8feb4594fc" } ], "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-83dc8d00-d097-43d2-a127-fb8dc617feb2" } ], "id": "41bb277d-7d1a-4a78-9827-0308c2a89384", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-41bb277d-7d1a-4a78-9827-0308c2a89384" }, { "name": "nova:3-multi", "item": [ { "name": "Nova 3 (Multi-Language)", "id": "a76d7d90-d7a9-4739-8319-704b0c0ade11", "protocolProfileBehavior": { "disableBodyPruning": true }, "request": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "eu-north-1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file", "value": null }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,ssn", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported language code. Nova 3 Multi auto-detects language; only `multi` is accepted. (This can only be one of multi)", "key": "language", "value": "multi", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-multi", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-multi" ] }, "description": "Transcribe multi-language audio using SLNG-hosted Deepgram Nova 3." }, "response": [ { "id": "91d84ec5-57de-437c-b0bf-4a6aa919dc50", "name": "Transcription successful.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "eu-north-1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,ssn", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported language code. Nova 3 Multi auto-detects language; only `multi` is accepted. (This can only be one of multi)", "key": "language", "value": "multi", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-multi", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-multi" ] } }, "status": "OK", "code": 200, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"results\": {\n \"channels\": [\n {\n \"alternatives\": [\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n },\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n }\n ],\n \"detected_language\": \"\"\n },\n {\n \"alternatives\": [\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n },\n {\n \"transcript\": \"\",\n \"confidence\": \"\"\n }\n ],\n \"detected_language\": \"\"\n }\n ]\n },\n \"metadata\": {\n \"request_id\": \"\",\n \"model\": \"\"\n }\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-91d84ec5-57de-437c-b0bf-4a6aa919dc50" }, { "id": "c811b698-5943-411f-ab50-b431b9bf32af", "name": "Bad request - invalid parameters provided.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "eu-north-1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,ssn", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported language code. Nova 3 Multi auto-detects language; only `multi` is accepted. (This can only be one of multi)", "key": "language", "value": "multi", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-multi", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-multi" ] } }, "status": "Bad Request", "code": 400, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-c811b698-5943-411f-ab50-b431b9bf32af" }, { "id": "74b30ed3-ff54-4479-a76d-9a9b10d292df", "name": "Invalid or missing API key.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "eu-north-1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,ssn", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported language code. Nova 3 Multi auto-detects language; only `multi` is accepted. (This can only be one of multi)", "key": "language", "value": "multi", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-multi", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-multi" ] } }, "status": "Unauthorized", "code": 401, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-74b30ed3-ff54-4479-a76d-9a9b10d292df" }, { "id": "832de92c-5ae5-4f82-9d75-2940b9ecd817", "name": "Audio file exceeds size limit.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "eu-north-1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,ssn", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported language code. Nova 3 Multi auto-detects language; only `multi` is accepted. (This can only be one of multi)", "key": "language", "value": "multi", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-multi", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-multi" ] } }, "status": "Request Entity Too Large", "code": 413, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-832de92c-5ae5-4f82-9d75-2940b9ecd817" }, { "id": "78cc0b43-5492-4eab-a3a2-ee6837f3100f", "name": "Internal server error from the provider.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "eu-north-1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,ssn", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported language code. Nova 3 Multi auto-detects language; only `multi` is accepted. (This can only be one of multi)", "key": "language", "value": "multi", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-multi", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-multi" ] } }, "status": "Internal Server Error", "code": 500, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-78cc0b43-5492-4eab-a3a2-ee6837f3100f" }, { "id": "0bdd5618-6ee4-460d-b3ef-9293c54abd04", "name": "Service unavailable.", "originalRequest": { "method": "POST", "header": [ { "description": "Target region override. Auto-selected if not provided.", "key": "X-Region-Override", "value": "eu-north-1" }, { "key": "Content-Type", "value": "multipart/form-data" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "formdata", "formdata": [ { "description": "Audio file (multipart) or base64-encoded audio (JSON).", "key": "audio", "type": "file" }, { "description": "Publicly accessible audio URL.", "key": "url", "value": "", "type": "text" }, { "description": "Model name override.", "key": "model", "value": "nova-3", "type": "text" }, { "description": "Enable partial/interim transcription results for streaming.", "key": "enable_partials", "value": "true", "type": "text" }, { "description": "Add punctuation and capitalization.", "key": "punctuate", "value": "false", "type": "text" }, { "description": "Apply formatting to improve readability (dates, times, numbers, etc.).", "key": "smart_format", "value": "false", "type": "text" }, { "description": "Segment transcript into utterances.", "key": "utterances", "value": "false", "type": "text" }, { "description": "Add paragraph formatting.", "key": "paragraphs", "value": "false", "type": "text" }, { "description": "Convert spoken numbers to digits.", "key": "numerals", "value": "false", "type": "text" }, { "description": "Filter profanity from transcript.", "key": "profanity_filter", "value": "false", "type": "text" }, { "description": "Redact sensitive information (pci, ssn, numbers).", "key": "redact", "value": "ssn,ssn", "type": "text" }, { "description": "Auto-detect spoken language.", "key": "detect_language", "value": "false", "type": "text" }, { "description": "Include filler words (uh, um) in transcript.", "key": "filler_words", "value": "false", "type": "text" }, { "description": "Enable multi-channel audio processing.", "key": "multichannel", "value": "false", "type": "text" }, { "description": "Keywords to boost recognition accuracy.", "key": "keywords", "value": ",", "type": "text" }, { "description": "Input audio encoding. (This can only be one of linear16,flac,mulaw,amr-nb,amr-wb,opus,speex,mp3,mp4,webm,aac,ogg)", "key": "encoding", "value": "linear16", "type": "text" }, { "description": "Input audio sample rate in Hz.", "key": "sample_rate", "value": "16000", "type": "text" }, { "description": "Number of audio channels.", "key": "channels", "value": "", "type": "text" }, { "key": "endpointing", "value": "", "type": "text" }, { "description": "Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.", "key": "utterance_end_ms", "value": "1000", "type": "text" }, { "description": "Tag for request tracking.", "key": "tag", "value": "", "type": "text" }, { "description": "Supported language code. Nova 3 Multi auto-detects language; only `multi` is accepted. (This can only be one of multi)", "key": "language", "value": "multi", "type": "text" } ] }, "url": { "raw": "{{baseUrl}}/v1/stt/slng/deepgram/nova:3-multi", "host": [ "{{baseUrl}}" ], "path": [ "v1", "stt", "slng", "deepgram", "nova:3-multi" ] } }, "status": "Service Unavailable", "code": 503, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"error\": \"\",\n \"status\": \"\",\n \"details\": \"\"\n}", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-0bdd5618-6ee4-460d-b3ef-9293c54abd04" } ], "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-a76d7d90-d7a9-4739-8319-704b0c0ade11" } ], "id": "99951a09-e9e3-49cd-aa9c-c562bff8e1aa", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-99951a09-e9e3-49cd-aa9c-c562bff8e1aa" } ], "id": "1f1874cb-ae3e-447c-8fd7-8133beeac496", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-1f1874cb-ae3e-447c-8fd7-8133beeac496" } ], "id": "74a56351-e80b-4396-8be0-e6bc88515efe", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-74a56351-e80b-4396-8be0-e6bc88515efe" } ], "id": "4bfdb40e-62f8-4195-8764-ad116bcfd241", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-4bfdb40e-62f8-4195-8764-ad116bcfd241" } ], "id": "004b6305-c3cc-4431-9332-10fad2e2d9da", "createdAt": "2026-07-28T02:55:31.000Z", "updatedAt": "2026-07-28T02:55:31.000Z", "uid": "35240-004b6305-c3cc-4431-9332-10fad2e2d9da" } ], "auth": { "type": "bearer", "bearer": [ { "key": "token", "value": "{{bearerToken}}", "type": "string" } ] }, "variable": [ { "key": "baseUrl", "value": "https://api.agents.slng.ai" } ] }