# FineVoice API

- [Overview of FineVoice](https://api.finevoice.ai/index.md): Create Expressive AI Voices in Seconds — Clone, Design, and Customize for Every Style and Scenario.
- [Quickstart](https://api.finevoice.ai/quickstart.md): Generate your first AI voice with FineVoice in minutes
- [Changelog](https://api.finevoice.ai/changelog.md): Stay tuned for the latest features and updates from FineVoice!
- [FineVoice API Pricing](https://api.finevoice.ai/essentials/api-pricing.md): Choose the plan that fits your project. Enjoy reliable, high-quality AI voices with flexible usage and easy scaling.
- [Brand Guidelines](https://api.finevoice.ai/guides/resources/brand-guidelines.md): Design guidelines for using FineVoice brand assets
- [Introduction](https://api.finevoice.ai/api-reference/introduction.md): Everything you need to know to get started with the FineVoice API
- [Podcast Speakers](https://api.finevoice.ai/api-reference/podcast-speakers.md): Available AI speakers for Podcast Generation. Use the speaker name (lowercase) in the `speakers` array of your podcast request.
- [Emotion Tags](https://api.finevoice.ai/api-reference/emotion-tags.md): Control tone and emotion in Text to Speech using Fish.Audio emotion tags.
- [MCP Server](https://api.finevoice.ai/api-reference/mcp.md): Connect AI clients to FineVoice's voice, music, and audio processing capabilities via the Model Context Protocol (MCP)
- [Text-to-Speech (TTS)](https://api.finevoice.ai/api-reference/endpoint/tts.md): Convert text into natural-sounding speech using a selected AI voice model.
- [Voice Conversion](https://api.finevoice.ai/api-reference/endpoint/voice-conversion.md): Transform the voice in an audio file to a different AI voice while preserving the original content.
- [Speech to Text](https://api.finevoice.ai/api-reference/endpoint/stt.md): Transcribe speech from an audio or video URL into text, with optional speaker diarization and word-level timestamps.
- [Sound Effect Generation](https://api.finevoice.ai/api-reference/endpoint/sfx-generation.md): Generate royalty-free sound effects from a text prompt or video source.
- [Audio Separation](https://api.finevoice.ai/api-reference/endpoint/separation.md): Separate vocals, instruments, and other audio stems from an audio file using AI.
- [Podcast Generation](https://api.finevoice.ai/api-reference/endpoint/podcastgen.md): Generate a multi-speaker AI podcast from a script or prompt, with selectable voice models for each speaker.
- [Get Task Status](https://api.finevoice.ai/api-reference/endpoint/task-status.md): Poll the status and result of an asynchronous audio processing task.
- [List AI Voices (Paginated)](https://api.finevoice.ai/api-reference/ai-voices/getvoices.md): Retrieve a paginated, filterable list of available AI voice models.
- [Get Voice Detail](https://api.finevoice.ai/api-reference/endpoint/changeaudiofile.md): Retrieve detailed information about a specific voice model by its name.
- [Voice Design](https://api.finevoice.ai/api-reference/endpoint/voice-design.md): Design a new AI voice from a text prompt and preview it with sample text.
- [Train Voice Model](https://api.finevoice.ai/api-reference/endpoint/trainmodel.md): Create a custom AI voice model by providing a training audio URL and basic profile information.
- [List AI Voices](https://api.finevoice.ai/api-reference/endpoint/listmodels.md): Retrieve a paginated, filterable list of available AI voice models.
- [Background Music Generation](https://api.finevoice.ai/api-reference/endpoint/music-gen-by-prompt.md): Generate a royalty-free background music track from a text prompt, with control over style, duration, and model version.
- [Music Generation](https://api.finevoice.ai/api-reference/endpoint/music-gen.md): Generate a full music track with vocals and/or instrumentation from lyrics, style description, and reference tracks.
- [Music Cover](https://api.finevoice.ai/api-reference/endpoint/music-cover.md): Create an AI voice cover of a song by replacing the original vocals with a target AI voice model.
- [Speech Enhancement](https://api.finevoice.ai/api-reference/endpoint/speech-enhancement.md): Reduce background noise and enhance speech quality. Supports WAV/MP3/FLAC/AAC/OGG/OPUS/M4A/WEBM.
- [Speech Super Resolution](https://api.finevoice.ai/api-reference/endpoint/speech-super-resolution.md): Upsample low-quality audio from 8 kHz to 48 kHz using AI super resolution.
- [Speech Separation](https://api.finevoice.ai/api-reference/endpoint/enhancer-separation.md): Separate two speakers from a mixed audio file. Use speaker_index (0 or 1) to select which speaker to return.
- [Remove Mouth Sounds](https://api.finevoice.ai/api-reference/endpoint/remove-mouth-sounds.md): Remove mouth sounds (clicks, pops, breathing) from audio using RNNoise, Hush, or Whisper-based detection.
- [Remove Long Silences](https://api.finevoice.ai/api-reference/endpoint/remove-long-silences.md): Detect and trim silence segments exceeding a threshold duration while preserving boundary silence to avoid abrupt cuts.
- [Filler Words — Detect](https://api.finevoice.ai/api-reference/endpoint/filler-words-detect.md): Detect filler words (um, uh, er, hmm) in audio and return their timestamps.
- [Filler Words — Remove](https://api.finevoice.ai/api-reference/endpoint/filler-words-remove.md): Detect and remove filler words from audio. Returns cleaned audio file.
- [Stuttering Remove](https://api.finevoice.ai/api-reference/endpoint/stuttering-remove.md): Detect and remove stuttering segments from audio using Whisper ASR. Returns processed audio file.
- [Audio Normalization](https://api.finevoice.ai/api-reference/endpoint/audio-normalization.md): Normalize audio loudness using peak, RMS, or combined normalization methods.
- [Process Pipeline](https://api.finevoice.ai/api-reference/endpoint/enhancer-pipeline.md): All-in-one audio processing pipeline. Select steps via boolean flags. Returns a download URL for the processed audio.

## OpenAPI Specs

- [changeaudiofile](/api-reference/changeaudiofile.json)
- [changeprogress](/api-reference/changeprogress.json)
- [createaudiofilechanger](/api-reference/createaudiofilechanger.json)
- [getvoicedetail](/api-reference/getvoicedetail.json)
- [listmodels](/api-reference/listmodels.json)
- [openapi](/api-reference/openapi.json)
- [pagevoices](/api-reference/pagevoices.json)
- [removefasttrainmodel ](/api-reference/removefasttrainmodel .json)
- [trainmodel](/api-reference/trainmodel.json)
- [uploadaudiofile](/api-reference/uploadaudiofile.json)

## Optional

- [Documentation](https://finevoice.ai/guide)
- [Blog](https://finevoice.ai/blog)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.