# LinkDigest > The social media search and reading layer for AI agents: one closed loop from > search to extraction. Search tools stop at a list of links and extraction tools > wait for a pasted link; LinkDigest does both. It finds posts on a topic > (Xiaohongshu, Douyin, YouTube, X and the web by search API; the user's own feed > from their own browser), then turns each social media URL into LLM-ready > context: transcript, on-screen text, image descriptions, caption and metadata, > as Markdown or JSON, with quotes checked against the post — in one call > (search_links with digest: true). > > A Chinese social media API for AI agents: Xiaohongshu (RedNote), Douyin, > Weibo, Hongguo (红果短剧 drama pages), WeChat Official Accounts, Bilibili and > 小宇宙 podcasts, plus TikTok, YouTube, X and Instagram. Not read today: > Zhihu, Kuaishou. Details: > https://linkdigest.dev/china-social-media-api ## What's new (2026-11-01) 红果短剧 (Hongguo, the short-drama app): a drama's page — hongguoduanju.com/detail?series_id= — and its series player page (…/player/, the address an episode opens at) are read from the site's own JSON: synopsis, tags, episode count, rating, likes / saves / heat, the rank label, the filing number (备案号) and the top written reviews. The episode itself is not read: the player ships its tracks CENC-encrypted, so a server-side read would mean defeating its content protection — play an episode in your own browser and read it with the extension. /series/ is answered, never fetched. Weibo (微博) posts are read: text, photos, video speech and on-screen text, counts and top comments, from a weibo.com or m.weibo.cn link, no Weibo account (https://linkdigest.dev/blog/weibo-api). A daily brief: name a topic and every morning its hottest new Xiaohongshu or Douyin posts are read, ranked by likes + 2×collects + comments, compared, and one post is written from them (POST /api/v1/watch; "reads" 1-20 posts a run). draft: true on a batch or search writes that post on demand, every figure in it checked against the notes. A video still being read answers 202 with an absolute poll_url and a Chinese and English next step. 2026-11-05: a finished Xiaohongshu or Douyin read in the console ends with a "watch this topic daily" card; on the console and the keyless look, a free account's long video that a full read would not cover is read transcript-first and whole (auto_depth says so, with the full price); the keyless read answers a video past the free look with the key, price and depth that read it (402). 2026-11-13: REST reads run side by side — a running read holds its own price once the link has been fetched (before, the dearest read the plan allows, which on a small balance was all of it and refused every other call with 429); the same POST for a link the account is already reading joins that read; a 429 for held credits lists the reads under "running", each with its poll URL. An unknown path under /api/v1 answers JSON 404 with the endpoint list (the balance is GET /api/v1/usage), and GET /api/v1/digest answers JSON 405 naming POST. 2026-11-12: the same switch for length — on the console and the keyless look, a free-plan video past the full-read cap (10 minutes) is read transcript-first, up to 60 minutes, whether or not the account holds pack credits (auto_depth.reason is "length"); before, a pack holder's long video stopped at 10 minutes. 2026-11-06: the public library — every console or keyless read of a public post (小红书, 抖音, B站, 微博, 公众号, YouTube, TikTok) with a title and three key points becomes a page at https://linkdigest.dev/d/: key points with checked quotes, hook, top comments, on-screen highlights, a transcript excerpt (the whole transcript after sign-in; a link already read costs 0 credits), the original linked; listings at https://linkdigest.dev/zh/wenan and https://linkdigest.dev/library. API, MCP and batch reads stay private. The keyless read now answers a video past the free look with its first window transcript-first plus the price of the rest, instead of a refusal. 2026-11-14: the signed-out look (the console on the site and the keyless read) is a 4-credit preview: an image post of up to ~24 images reads whole, a video its first minutes, with the price of the rest; signing in grants 10 credits once. Links already read stay free to everyone. 2026-11-06: Japanese pages (https://linkdigest.dev/ja) for Japanese teams working with the Chinese market — reading a 小紅書 post in Japanese (translate_to: "ja"), searching 小紅書 for a brand, region or product and ranking what it found, and transcribing a 抖音 video; card payment in USD. The same evening: a self-serve Japanese diagnosis (https://linkdigest.dev/ja/shindan), Japanese API docs, public city/theme reports (https://linkdigest.dev/ja/report), and six question-shaped explainers — 小紅書とは, 口コミの調べ方, 翻訳ツールの選び方, 訪日中国人の口コミ分析, 運用代行の費用相場, 中国SNS分析ツールの選び方 — each figure with its source. 2026-11-07: a video annotation API for world-model, VLA / robot-learning and video-generation teams (https://linkdigest.dev/annotation, Chinese: https://linkdigest.dev/zh/shipin-biaozhu): send your own video through /api/v1/capture (the file never leaves your machine) and ask for format "annotation" — timed speech, a frame every few seconds described in words, on-screen text with its time, key points with checked quotes; a batch exports as JSONL. Priced per hour from the per-minute credit; a pilot request form is on the page. A video without a sound track is read through its pictures. Five silent hands-on clips annotated this way are a public Hugging Face dataset: https://huggingface.co/datasets/JackChew/egocentric-video-annotation-sample (annotations CC BY 4.0, videos linked). 2026-11-07: B站网课 / 讲座转文字 (https://linkdigest.dev/zh/bilibili-wangke-zhuanwenzi): a whole lecture read transcript-first — measured on an 87-minute public paper reading: 9 min 16 s, 470 timed segments, 30,045 characters, 13 of 15 key points verified, 45 credits; a price table by length and depth, and how far the 10 free credits go (18 minutes transcript-first). Three generic Chinese pages answer the platform-agnostic searches: 视频链接转文字 (https://linkdigest.dev/zh/shipin-lianjie-zhuanwenzi), 视频文案提取 (https://linkdigest.dev/zh/shipin-wenan-tiqu, the speech-only price) and AI 总结视频 (https://linkdigest.dev/zh/ai-shipin-zongjie, key points with checked quotes, a summary prompt, MCP/Dify). 2026-11-07: 痛点雷达 Pain-Point Radar — one topic (a product, category or brand) → what people search for after it (Baidu, Taobao and Bing suggestions for market cn; Bing and YouTube for global), and what 12–48 posts and their top comments (cn: Xiaohongshu + Douyin; global: YouTube + TikTok, for 出海 sellers) complain about, want and ask: pain points, needs, purchase blockers, products, unanswered questions and gaps, each with count_posts (how many of the posts it came from, counted by code) and quotes checked word for word; a re-run of the topic says what changed. POST /api/v1/radar, poll GET /api/v1/radar/{id} (?format=md for Markdown); about 47 credits for a quick run. 2026-11-08: referral links — every account's billing page has https://linkdigest.dev/?ref=; when someone who signs up through it makes a first payment, the member gets 50 credits (at most 20 a month). The newcomer pays the normal price, no discount; the 10 free credits are unchanged. ## Earlier (2026-10-17) Search in front of read (search_links on Xiaohongshu, YouTube, X and the web; the extension on the user's own pages); the top comments on every Xiaohongshu note; consumer insight (insight=true) with every quote checked; many links as one comparison page (compare_links / synthesis); a browser extension that reads Douyin from the user's own tab; a Studio plan. Details: https://linkdigest.dev/blog/whats-new-october-2026 (中文: https://linkdigest.dev/blog/2026-10-gengxin). ## What problem it solves AI coding agents cannot read social media links. Share URLs are tokenised (xsec_token, app_code_link), the content is video or images rather than text, and fetching the URL returns an app-download shell instead of the post. LinkDigest resolves the link, reads the media, and returns text an agent can use. ## How to use it No key for the first look (2026-10-30) — one line, Markdown back: curl -sL https://linkdigest.dev/read/https://www.xiaohongshu.com/explore/ (-L matters for curl: the edge answers the // after the scheme with a 308 that collapses it, and the page it redirects to is the one that reads. fetch, requests and a browser follow it already. Or: https://linkdigest.dev/read/?u=). Returns `text/markdown`: title, attribution, the key points, the caption, the opening of the transcript, the images described. No key, no account, one uncached link per visitor; links already read are free and unmetered. YouTube is not on the free first look. A read still running answers 202 with a job id and a poll URL. MCP (Claude Code, Cursor, Cherry Studio, Trae, 通义灵码 — configs for each on https://linkdigest.dev/zh/docs): claude mcp add --transport http linkdigest https://linkdigest.dev/mcp \ --header "Authorization: Bearer ld_live_..." Tool: digest_url(url, format, job_id, partial_ok, translate_to, breakdown, depth, ask, insight) ask="…" answers one question from the post ("what products and prices does it recommend?") with the quotes the answer rests on, each checked against the post; found=false when the post does not say. 1 more credit. breakdown=true adds a 爆款拆解 teardown (hook, timed beats, title formula, reusable template; quotes checked against the post) for 1 more credit. insight=true adds the consumer insight (消费者洞察): audience, claims, objections, purchase-intent cues, products/prices, questions — each a quote checked against the post and its top comments (`insight` in json; found=false on a section the material does not support). 1 more credit. depth="transcript" reads a long video transcript-first; depth="script" takes the speech only (文案 only, see Pricing). A long video may need two calls: if the result names a job id, call digest_url again with job_id and no url to collect it. Tool: compare_links(urls, batch_id, insight, breakdown, translate_to) — up to 20 links read as one batch and compared in one page (批量综合): shared themes, hooks, formats, claims, objections and gaps, every example naming its link and checked against it. The first call returns a batch id; call again with batch_id to collect. Each link at its usual price; the comparison is 1 credit per 10 links. Needs a key. Clients that only run local (stdio) MCP servers: bridge with npx mcp-remote https://linkdigest.dev/mcp --header "Authorization:${AUTH_HEADER}" (AUTH_HEADER="Bearer ld_live_..."), or run the open-source Python stdio server from https://github.com/jcaiagent7143-ui/linkdigest-mcp (MIT; on PyPI: uvx linkdigest-mcp). The same package is a zero-dependency Python SDK with a `linkdigest` command line, an offline share-text parser (linkdigest.links), a LangChain tool and a LlamaIndex reader (pip install "linkdigest-mcp[langchain]" / "[llamaindex]", 0.2.5 or later). OpenAPI (Coze plugin import, GPT actions): https://linkdigest.dev/openapi.json REST: POST https://linkdigest.dev/api/v1/digest Authorization: Bearer ld_live_... {"url": "...", "format": "json" | "markdown"} Batches: POST https://linkdigest.dev/api/v1/digest/batch {"urls": [...]} — up to 10 links on the free plan, 50 on Dev, 200 on Studio; the same add-ons as a single call, plus "synthesis": true for one comparison over everything the batch read (批量综合, returned as the batch's `synthesis`; 1 credit per started 10 notes, once), and "draft": true for one post written from the batch after the comparison (成稿: three titles, body, hashtags, cover text, in the shape of "platform" xiaohongshu | douyin | en, in the creator's voice when "voice" carries a sample; every figure in it is in the notes; +1 credit once). Poll GET /api/v1/digest/batch/{id} or give a signed webhook_url. Daily brief: POST https://linkdigest.dev/api/v1/watch {"query": "露营装备", "platform": "xiaohongshu", "voice": "…", "reads": 10} — every day the topic's hottest new posts are read, ranked, compared, and one post is written from them (成稿) and mailed with a share link; about 8–12 credits a run, nothing on a day with nothing new. Free 1 topic, Dev 5, Studio 20. PATCH /api/v1/watch/{id} pauses, resumes or runs now; DELETE removes. Nothing is published for you. Pain-Point Radar (痛点雷达): POST https://linkdigest.dev/api/v1/radar {"topic": "扫地机器人", "market": "cn" | "global", "size": "quick" | "standard" | "deep", "language": "zh-CN", "weekly": false} → 202 {radar_id, estimate, poll}; GET /api/v1/radar/{id} → 202 while it searches, reads and aggregates, then the radar: sections pain, needs, blockers, products, open_questions, demand (search suggestions grouped by need) and gaps, each point {label, count_posts, count_comments, share, heat, quotes[{text, gloss, note, kind, verified}]}, a diff against the previous run of the topic, the posts read and a share_url. Billed as two searches, each post with insight, and the aggregation (3 for 12 posts, 6 for 48); fewer than 3 posts read, the aggregation is free. POST /api/v1/radar/preview {"topic", "market"}: the search suggestions alone, 1 credit. Not an MCP tool: call the REST endpoints. ## Discovery (topic → links → digests → one page) Two loops, because the platforms differ. - From a search API (xiaohongshu, douyin, youtube, x, web): Tool: search_links(query, platform, limit, digest, insight, breakdown) — a web search scoped to the platform, filtered to links digest_url can read. A search that finds posts costs 4 credits on douyin and xiaohongshu, 1 elsewhere; nothing found is free. Metered by credits, not by an hourly count; free accounts share 30 searches a day. With digest=true the results become a batch with a comparison, billed as a batch; then compare_links with the batch_id. For xiaohongshu this is the notes the web has indexed, each read from its public page (the page a logged-out phone gets): no login, no session, no signature. A subset of the platform, not the user's feed. For douyin (since 2026-10-21) it is the video pages the web has indexed, each read through Douyin's own embed player like a pasted link; Chinese words find the most. On both, results carry the words searched, newest first, each with posted_at (the day it went up). - From a page you can see (the user's own Xiaohongshu feed, or a search the web has not indexed): LinkDigest never holds the user's session. The user opens the page in their own browser and presses the browser extension's "Digest the notes on this page" button (https://linkdigest.dev/extension; on Douyin, "Digest this tab" on a video), choosing how many notes to read; it starts a batch from that tab, labelled with the page. For xiaohongshu, search_links hands the agent that same search as a link for the user's own browser (own_browser_url); the batch is named after the query. The agent then calls Tool: list_batches(limit, label) — the key's last batches, newest first, one line each (batch_id, label, created, status done/total, credits, synthesis) — and passes the newest batch_id to compare_links. REST: GET https://linkdigest.dev/api/v1/digest/batches?limit=10 and POST https://linkdigest.dev/api/v1/search {"query", "platform", "limit", "digest"}. A batch can carry a "label" (POST /api/v1/digest/batch) so a listing can name it. ## Platform coverage - Xiaohongshu (小红书): works, image notes and video notes, no login required - YouTube: works. YouTube blocks datacenter addresses, so the video is read by Gemini watching it directly; transcripts carry timecodes. - TikTok: works, including vt.tiktok.com short links - X (Twitter): works for posts with video or images - Bilibili (哔哩哔哩): works for videos and b23.tv short links since 2026-10-24. Bilibili returns HTTP 412 to every request from our servers' address, its own embed player included, so the player — the public page Bilibili publishes for other sites to embed — is rendered through a residential exit when the direct render is refused. No login, no cookies, no captcha. Private or deleted videos say so and are not charged; if every route is refused the read answers 503 with error_code platform_refused and how_to_read_now. - Web pages and articles: works - Douyin (抖音): works for pasted links again since 2026-10-21. Paste a link or the whole share text and it is read through Douyin's own embed player: the public player Douyin publishes for other sites, opened by a real browser on our side, which receives the post and its stream. No login, no cookies, no captcha. Douyin's web API still refuses the engine's signed requests (2026-10-09), so when the player will not serve a post the read answers 503 with error_code platform_refused and how_to_read_now, and is not billed; the routes are: save it in the app (Share → 保存本地) and upload it at https://linkdigest.dev/app/upload (signed in; the browser sends only its sound and a few frames), record it playing in your own tab with the extension (https://linkdigest.dev/extension), or API POST /api/v1/capture with the same parts. From a script: `linkdigest capture --url ` (pip install linkdigest-mcp) extracts the sound and 36 frames on the caller's machine and makes that call; the video is never uploaded. Docs: https://linkdigest.dev/docs#capture. - Instagram: works since 2026-10-24. Reels and video posts are read like any video (transcript, frames, on-screen text). Photo posts (/p/…) are read from Instagram's own embed page, the one it publishes for other sites, opened by a real browser on our side with no login and no cookies: the full caption, author, hashtags, like and comment counts, and the photo described and read for its text. A carousel gives its first slide; a private or removed post answers that it cannot be read, and is not billed. - Podcasts: works since 2026-10-29. 小宇宙 episode links (xiaoyuzhoufm.com/episode/…) and Apple Podcasts episode links (…?i=…) are read from the public episode page and feed with no login, as text: the transcript with times, show notes, the podcast and episode title, counts, and the top comments a 小宇宙 page shows. Always read at depth "script" (an episode has no frames): 1 credit per started 2 minutes, no base credit — a 45-minute episode is 23 credits. Paid episodes cannot be read and are not billed. Spotify is not supported: without a login it serves a 30-second preview. 喜马拉雅: not yet. ## Notable properties - Where a platform publishes captions, those are the transcript. Otherwise speech is transcribed with OpenAI's gpt-4o-mini-transcribe (since 2026-10-10, when the provider withdrew Qwen3-ASR, used until then). Its endpoint returns text without per-sentence times, so the engine splits each ~170 s chunk into sentences and estimates each sentence's start from its place in the chunk (`approx: true` on the segment and on any quote placed by it); on-screen text (`on_screen`) carries approximate times, accurate to a keyframe interval, and text shown for most of the video (title card, watermark) is listed once in `on_screen_persistent`. - What the platform says about a post comes back as it said it: `stats` (engagement counts), `tags` (hashtags), `comments` (the first comments the post's share page served with it — Xiaohongshu's top few, read with no login and no second request; never the thread; added 2026-10-17), `chapters` with `chapter_source` ("author", or "platform" for Douyin's generated chapters, each with a one-line summary; never inferred, and on a partial read only those in the part read), `category` (the platform's own, broadest first) and `music` (a soundtrack that is not the poster's own voice). The last four were added 2026-10-05 and are absent on links cached before then. - A long video comes with a timed outline (`outline`, added 2026-11-10): when the transcript runs 8 minutes or more and the video has no marked chapters, 5 to 20 sections `{ start, end, title, summary[], quote, generated }`, in order, covering everything read. The model proposes where to cut; code makes the sections contiguous, snaps each start and end to a transcript line's own time, and keeps a quote only when it is found in that section (`generated: "fallback"` = equal stretches titled by their opening words). No extra credit; also in raw_markdown under "## Outline / 大纲". A multi-part Bilibili video (分P) also carries `parts` `{ count, current, items: [{ p, title, seconds }] }`: read another part by sending the same link with ?p=, or several as a batch. - Image posts are read image by image, every one up to 60 a read (a Xiaohongshu note, a Douyin 图文, a WeChat article), priced per 6 images. Past 60, the first 60 are taken and priced, and `degraded` names the rest; `image_count` and `images_read` carry the two numbers (added 2026-10-05). `images_read` is what was taken and priced, not what was read: an image whose download or vision read failed still counts, and `coverage.images_read` is how many came back read. With `partial_ok`, a post the budget does not cover whole takes its first images (6 a credit) and carries `partial` with 0 seconds (since 2026-10-06). A WeChat article does so even without `partial_ok`. - Every digest carries a coverage receipt, `coverage`, computed in code and never by a model: for video, `seconds_transcribed` of `duration_seconds` and `largest_frame_gap_seconds`; for image posts, `images_read` of `images_total`; and `not_captured`, plain statements of what was not read ("minutes 12:00-43:58 not read (budget)", "3 of 21 images skipped", "comments not read"). The Markdown shows it as a Coverage section. - Each key point can be checked: `key_point_support` holds one short quote per key point ({ point_index, kind, t, image_index, quote, verified }), with kind transcript, on_screen, image, caption or chapter. The engine looks every quote up in the post; one it cannot find is kept with verified false. Both fields were added 2026-10-05 and are absent on links cached before then. - What the post points to comes back as `links` ({ url, found_in, label, kind }): URLs in its caption or YouTube description, a WeChat article's 阅读原文, QR codes decoded from the images and frames the read downloaded, well-formed URLs in on-screen text, and chapters. Deduplicated, at most 20 (`coverage.links_found` counts them all), and never opened: reading one is a separate digest, at its own price, if you choose it. `kind` is web, payment (WeChat Pay, Alipay…), group_invite (WeChat, QQ, Telegram groups…), app_deeplink or other, so a payment code or group invite is never mistaken for a page. Added 2026-10-05; absent on links cached before then. - Media is never stored or served. Only the text digest is retained. - A blocked or removed post returns an error rather than a description of the error page. - Every response carries a `degraded` array. It names anything that did not read fully, and also notes the route a complete read took ("read via oEmbed", "read by Gemini watching the video directly") — so a non-empty array is not by itself a failed read. - Rate limit: 60 API/MCP calls per hour per account. - Per-platform health is public: GET https://linkdigest.dev/api/v1/health/platforms returns, for each platform, its state, an ok/degraded/unknown status, when a real post on it was last read in full, and the last 30 days counted from real requests: reads_30d, whole_rate_30d (share that came back whole, with failures on our side counted against us; null under 20 attempts) and p50_seconds. No key needed. - Cached links are served free and do not count against a plan allowance. - Any link shape the app gives you works: share-button short links, full page addresses, a profile page with the post open (douyin ?modal_id=, xiaohongshu /user/profile/…), and the whole share-sheet text — the first link is extracted. A Xiaohongshu page address without its xsec_token is the least reliable shape — Xiaohongshu often answers it with a login wall, though it reads sometimes; copy the link from the share sheet to be sure. ## Connect from a personal agent (Muse, Grok Bot, Manus Cue, Hermes, OpenClaw, Claude Code, Cursor) Any agent that takes a remote MCP server can use LinkDigest: add https://linkdigest.dev/mcp with header "Authorization: Bearer ld_live_...". ChatGPT connectors (developer mode), claude.ai, Claude Desktop and Claude Code can sign in instead (2026-11-09): add https://linkdigest.dev/mcp/oauth and choose OAuth; the person signs in to LinkDigest, approves once, and the client gets a key for their account (revocable in /app/keys). Without a key the digest_url tool returns a summary (two a day per address). Step-by-step per agent: https://linkdigest.dev/connect ## Pricing (billed in credits, not digests) A competitor report (竞品洞察报告) is a batch with insight=true and synthesis=true: every note's consumer insight plus one comparison. Each note at its own price (typically 2) + 1 for insight, plus the comparison: 3 notes come to about 10 credits. Console sizes: 3 free, 20 Dev, 50 Studio. In one line: $0.02 an image post, $0.02 per minute of video, 10 free on sign-up. Without an API key, POST /api/v1/digest and the MCP tool return a summary (two a day per address); POST /api/v1/keys/request {"email"} mails a link that issues a key. Free: 10 credits once per person, when the account is created — they do not renew. No card. A new account opened from a network where another account used its free credits up in the last 7 days starts without them (402 with the price). The current figure is always on https://linkdigest.dev/pricing. Requires a free account (Google sign-in or an emailed magic link). Credit pack: $5 once for 250 credits, no subscription, credits never expire; spent only after the plan's own allowance. The pack can be paid with Alipay (支付宝, charged in yuan: ¥36). Per call in yuan at that pack's rate (按次价格): a one-minute Douyin video, speech only ≈ ¥0.144/次; the same video read in full ≈ ¥0.288/次; a Xiaohongshu image note or a WeChat article of up to 6 images ≈ ¥0.144/次; a ten-minute Bilibili video, speech only ≈ ¥0.72/次. A link anyone has read before costs nothing. Starter pack: $1.5 (¥9.9) once for 50 credits, Alipay or card. Dev: $9/month for 500 credits a month (card); batches of 50 links, 60 calls an hour. Dev pass (月卡), for buyers who pay with Alipay: ¥65 once for 30 days of Dev (the same 500 credits and limits). It does not renew by itself; pack credits are untouched when it ends. Studio: $49/month for 3500 credits (card); batches of 200 links, 300 calls an hour. Volume pack for buyers in China: ¥288 once for 2000 credits (Alipay), no subscription. Add-ons per link: translate_to +1, breakdown +1, ask +1, insight +1; a batch's synthesis 1 credit per started 10 notes, once. An extension capture ("Digest this tab") is billed like a link of that length, and so is an uploaded video: 1 per started minute. Finding posts (search_links, POST /api/v1/search) costs 4 credits on douyin and xiaohongshu and 1 elsewhere when it finds posts, 0 otherwise (metered by credits, not an hourly count; free accounts share 30 searches a day); the extension's button is free. The share page's top comments come with a Xiaohongshu note at no charge. A typical post costs 1 credit, which covers the first 6 images; video costs 1 credit per started minute on top -- so 500 credits is nowhere near 500 videos. Cached links cost 0 credits. A digest that read nothing is not charged. Long videos: `depth: "transcript"` (REST, batch and MCP; added 2026-10-05) reads a video transcript-first -- the whole transcript plus about one frame a minute (one per chapter when it has chapters) -- for 1 credit per started 2 minutes instead of 1 per minute, and up to 120 minutes on a paid plan (60 free) against 30 (10) for a full read. The digest says `depth`, and `coverage.not_captured` says how sparse the frames were. When a full read comes back partial, `partial.transcript_credits` is what the whole video costs transcript-first. A YouTube video read by Gemini has no transcript-only form: it is read and priced in full. The words only: `depth: "script"` (added 2026-10-29) reads the speech and nothing else -- no frames, no on-screen text -- for 1 credit per started 2 minutes with no base credit: a 5-minute video is 3 credits (6 full). With no depth given, an `ask` for the words only (文案, 口播, 逐字稿, "script") is read this way. ## Links - [Docs](https://linkdigest.dev/docs) - [Pricing](https://linkdigest.dev/pricing) - [For businesses across Asia](https://linkdigest.dev/business) — what Chinese visitors say about you on Xiaohongshu, as a report in English, Japanese or Korean - [Platforms](https://linkdigest.dev/platforms) - [Data sourcing & compliance](https://linkdigest.dev/data-sourcing) — how each platform is opened (embed players, residential exits named), what is stored and for how long, what a refusal answers - [Xiaohongshu (RedNote) to text for LLMs — transcript, OCR, top comments, consumer insight](https://linkdigest.dev/platforms/xiaohongshu) - [Douyin to text for LLMs — search Douyin by topic, spoken transcript, timed on-screen text](https://linkdigest.dev/platforms/douyin) - [Weibo (微博) to text for LLMs — post text, photos, video, top comments](https://linkdigest.dev/platforms/weibo) - [YouTube to text for LLMs — captions or a watched transcript](https://linkdigest.dev/platforms/youtube) - [TikTok to text for LLMs — transcript, frames, on-screen text](https://linkdigest.dev/platforms/tiktok) - [X (Twitter) to text for LLMs — post text, photo descriptions, transcript](https://linkdigest.dev/platforms/x) - [Bilibili (B站) video to text for LLMs — spoken transcript, on-screen text, tags and counts](https://linkdigest.dev/platforms/bilibili) - [Writing](https://linkdigest.dev/blog) — [feed](https://linkdigest.dev/blog/feed.xml) - [Translate a Douyin video into English: the speech, the on-screen text and the caption](https://linkdigest.dev/blog/douyin-translate-to-english) - [What buyers complain about robot vacuums: 11 YouTube and TikTok reviews, counted](https://linkdigest.dev/blog/what-buyers-complain-about-robot-vacuums) - [扫地机器人有哪些缺点?读完小红书和抖音 12 篇热门内容,数出来的痛点、需求和没人回答的问题](https://linkdigest.dev/blog/saodi-jiqiren-tongdian-leida) - [What Chinese tourists say about Japan on RedNote: seven public reports (Osaka, Kyoto, Hokkaido, Fukuoka, Okinawa, onsen, tax-free shopping)](https://linkdigest.dev/blog/what-chinese-tourists-say-about-japan-on-rednote) - [RedNote (Xiaohongshu) analytics for foreign brands: what you can measure from public notes without an account](https://linkdigest.dev/blog/rednote-analytics-for-foreign-brands) - [How to search RedNote (Xiaohongshu) from outside China — and why Chinese keywords find more](https://linkdigest.dev/blog/how-to-search-rednote-in-english) - [RedNote competitor analysis: read 10 notes about a category in one call and get one comparison](https://linkdigest.dev/blog/rednote-competitor-analysis) - [Xiaohongshu / RedNote API pricing explained: what one read costs, the free tier, and when it is cheaper than a scraper](https://linkdigest.dev/blog/xiaohongshu-api-pricing-explained) - [Xiaohongshu (RedNote) comments API: the top comments and their replies from a note link — what you get, what you don't](https://linkdigest.dev/blog/xiaohongshu-comments-api) - [Xiaohongshu (RedNote) search API: find the posts on a topic, read them in full and rank them by engagement in one call](https://linkdigest.dev/blog/xiaohongshu-search-api-hottest-posts) - [每天早上,赛道里最火的 5 条小红书笔记已经读好、稿也写好了:用一个接口订阅「赛道日报」(附实测两次运行和 curl)](https://linkdigest.dev/blog/saidao-ribao-meitian-zaoshang) - [A daily brief for a Xiaohongshu or Douyin topic: the hottest new posts read, ranked and turned into a draft before you wake up (one API call, two runs measured)](https://linkdigest.dev/blog/daily-brief-xiaohongshu-douyin-topic) - [Bilibili transcript: get the transcript of a Bilibili video from its link, with or without CC subtitles](https://linkdigest.dev/blog/bilibili-transcript) - [Xiaohongshu (RedNote) scraper: what fetching a post takes in 2026, and an API that returns the text instead](https://linkdigest.dev/blog/xiaohongshu-scraper) - [RedNote image to text: get the text out of every image in a RedNote (Xiaohongshu) post](https://linkdigest.dev/blog/rednote-image-to-text) - [抖音分享链接打开跳到首页,或提示「因作品权限或已被删除,无法观看」?三种结果怎么分辨](https://linkdigest.dev/blog/douyin-fenxiang-lianjie-tiao-shouye) - [Douyin share link opens the home page, or says 「因作品权限或已被删除,无法观看」? Three outcomes, told apart](https://linkdigest.dev/blog/douyin-share-link-opens-homepage) - [Translate a RedNote post into English: the caption, the text in its images and the video's speech](https://linkdigest.dev/blog/rednote-translate) - [小红书笔记链接打开是 404、「页面不见了」或 300031?先看链接里有没有 xsec_token](https://linkdigest.dev/blog/xiaohongshu-xsec-token-404) - [Xiaohongshu (RedNote) note link returns 404 or error 300031? Check the xsec_token](https://linkdigest.dev/blog/xiaohongshu-xsec-token) - [Weibo API: read a Weibo (微博) post as text — without the open platform or a scraper](https://linkdigest.dev/blog/weibo-api) - [RedNote transcript: get the transcript of a RedNote (Xiaohongshu) video from its link](https://linkdigest.dev/blog/rednote-transcript) - [Xiaohongshu (RedNote) API: note text, image OCR, comments and video transcripts](https://linkdigest.dev/blog/xiaohongshu-rednote-api) - [Douyin video transcript API: the spoken script (文案) of any Douyin video, with timestamps](https://linkdigest.dev/blog/douyin-video-transcript-api) - [一次读几十条:批量把一批链接变成一页对比](https://linkdigest.dev/blog/batch-dozens-of-links-one-page) - [Why ChatGPT and Claude can't open Xiaohongshu or Douyin links — and what works](https://linkdigest.dev/blog/why-chatgpt-cant-open-xiaohongshu-douyin-links) - [抖音分享出来的那一串,不是一个链接](https://linkdigest.dev/blog/douyin-share-text-is-not-a-link) - [微信公众号文章:长链接会撞验证码,短链接不会](https://linkdigest.dev/blog/wechat-article-links-long-vs-short) - [Opening a café in Penang: what a research assistant found in 90 seconds](https://linkdigest.dev/blog/research-assistant-penang-cafe) - [在槟城开咖啡馆:研究助手 90 秒看完了同行](https://linkdigest.dev/blog/yanjiu-zhushou-bincheng-kafeiguan) - [What's new in LinkDigest, October 2026](https://linkdigest.dev/blog/whats-new-october-2026) - [LinkDigest 十月更新:先搜再读、热评、消费者洞察、批量综合、浏览器扩展](https://linkdigest.dev/blog/2026-10-gengxin) - [Five ways people use LinkDigest, told from their side](https://linkdigest.dev/blog/five-ways-people-use-linkdigest) - [LinkDigest 用户故事:五种用法,用客户的口吻讲](https://linkdigest.dev/blog/linkdigest-yonghu-gushi) - [What is xhslink? Xiaohongshu's two share-link domains, and the one that fails silently](https://linkdigest.dev/blog/xiaohongshu-share-links-have-two-domains) - [Reading links your agent can't open](https://linkdigest.dev/blog/reading-social-links-from-an-agent) - [What it actually takes to read a Xiaohongshu post from a server](https://linkdigest.dev/blog/reading-xiaohongshu-from-a-server) - [Per-platform health, no key](https://linkdigest.dev/api/v1/health/platforms) — state, an ok/degraded/unknown status and when a real post was last read in full. Also listed on (the same hosted service; all but Apify use your LinkDigest key): - Official MCP registry: [dev.linkdigest/linkdigest](https://registry.modelcontextprotocol.io/v0/servers/dev.linkdigest%2Flinkdigest/versions) - ModelScope MCP 广场 (hosted, deployable): [JCAI714/linkdigest](https://modelscope.cn/mcp/servers/JCAI714/linkdigest) - Dify plugin: [linkdigest](https://marketplace.dify.ai/plugins/jcaiagent7143-ui/linkdigest) - Apify Store actors (billed through Apify, no LinkDigest key): [Douyin video to text](https://apify.com/loongnian714/douyin-video-to-text) , [Xiaohongshu note to text](https://apify.com/loongnian714/xiaohongshu-note-to-text) , [social URL to LLM text](https://apify.com/loongnian714/social-url-to-llm-text) - ClawHub skills (Chinese): [小红书笔记 OCR](https://clawhub.ai/jackchew7143/skills/linkdigest-xhs-note-ocr) , [视频逐字稿](https://clawhub.ai/jackchew7143/skills/linkdigest-video-transcript) , [爆款拆解](https://clawhub.ai/jackchew7143/skills/linkdigest-viral-breakdown) Chinese pages (Simplified Chinese, written for 运营 and developers, not translations): - [首页](https://linkdigest.dev/zh) - [小红书笔记提取](https://linkdigest.dev/zh/xiaohongshu-biji-tiqu) - [抖音文案提取](https://linkdigest.dev/zh/douyin-wenan-tiqu) - [抖音视频总结](https://linkdigest.dev/zh/douyin-shipin-zongjie) - [抖音去水印替代](https://linkdigest.dev/zh/douyin-qu-shuiyin-tidai) - [ChatGPT 打不开小红书抖音](https://linkdigest.dev/zh/chatgpt-du-xiaohongshu-douyin) - [小红书有官方 API 吗](https://linkdigest.dev/zh/xiaohongshu-guanfang-api) - [小红书 MCP](https://linkdigest.dev/zh/xiaohongshu-mcp) - [对标账号拆解](https://linkdigest.dev/zh/duibiao-zhanghao) - [API / MCP 文档](https://linkdigest.dev/zh/docs) - [Dify 研究工作流](https://linkdigest.dev/zh/docs/dify) - [接入个人 agent](https://linkdigest.dev/zh/jieru) - [小红书视频转文字](https://linkdigest.dev/zh/xiaohongshu-shipin-zhuanwenzi) - [抖音口播提取](https://linkdigest.dev/zh/douyin-koubo-tiqu) - [TikTok 字幕提取](https://linkdigest.dev/zh/tiktok-zimu-tiqu) - [YouTube 视频转文字](https://linkdigest.dev/zh/youtube-zhuanwenzi) - [X / 推特帖子提取](https://linkdigest.dev/zh/x-tuiwen-tiqu) - [抖音 MCP](https://linkdigest.dev/zh/douyin-mcp) - [小红书图片文字提取 API](https://linkdigest.dev/zh/xiaohongshu-tupian-wenzi-tiqu) - [抖音文案提取 API](https://linkdigest.dev/zh/douyin-wenan-api) - [爆款拆解 API](https://linkdigest.dev/zh/baokuan-chaijie-api) - [竞品对比](https://linkdigest.dev/zh/tikhub-redfox-socialdatax-duibi) - [公众号文章提取 API](https://linkdigest.dev/zh/gongzhonghao-wenzhang-tiqu) - [长视频转文字 API](https://linkdigest.dev/zh/changshipin-zhuanwenzi) - [浏览器扩展](https://linkdigest.dev/zh/liulanqi-kuozhan) - [抖音视频搜索 API](https://linkdigest.dev/zh/douyin-sousuo-api) - [Instagram 帖子提取](https://linkdigest.dev/zh/instagram-tiezi-tiqu) - [研究助手](https://linkdigest.dev/zh/yanjiu-zhushou) - [小红书市场调研](https://linkdigest.dev/zh/xiaohongshu-shichang-diaoyan) - [开店前调研](https://linkdigest.dev/zh/kaidian-qian-diaoyan) - [小宇宙播客转文字](https://linkdigest.dev/zh/xiaoyuzhou-boke-zhuanwenzi) - [抖音文案提取工具哪个好](https://linkdigest.dev/zh/douyin-wenan-tiqu-gongju) - [批量提取抖音文案](https://linkdigest.dev/zh/douyin-wenan-piliang-tiqu) - [n8n 读小红书/抖音](https://linkdigest.dev/zh/n8n-xiaohongshu-douyin) - [抖音字幕提取](https://linkdigest.dev/zh/douyin-zimu-tiqu) - [B站视频AI总结](https://linkdigest.dev/zh/bilibili-ai-zongjie) - [博主系列视频转文字](https://linkdigest.dev/zh/bozhu-xilie-shipin-zhuanwenzi) - [B站字幕提取](https://linkdigest.dev/zh/bilibili-zimu-tiqu) - [小红书数据分析工具](https://linkdigest.dev/zh/xiaohongshu-shuju-fenxi-gongju) - [抖音数据分析工具](https://linkdigest.dev/zh/douyin-shuju-fenxi-gongju) - [抖音小红书链接解析](https://linkdigest.dev/zh/lianjie-jiexi) - [公众号文章转Markdown](https://linkdigest.dev/zh/gongzhonghao-zhuan-markdown) - [公众号文章API](https://linkdigest.dev/zh/gongzhonghao-wenzhang-api) - [B站视频转文字API](https://linkdigest.dev/zh/bilibili-zhuanwenzi-api) - [B站视频提取PPT](https://linkdigest.dev/zh/bilibili-ppt-tiqu) - [B站视频翻译](https://linkdigest.dev/zh/bilibili-shipin-fanyi) - [抖音视频翻译](https://linkdigest.dev/zh/douyin-shipin-fanyi) - [抖音带货视频文案提取](https://linkdigest.dev/zh/douyin-daihuo-wenan-tiqu) - [YouTube 视频翻译](https://linkdigest.dev/zh/youtube-shipin-fanyi) - [小红书视频总结](https://linkdigest.dev/zh/xiaohongshu-shipin-zongjie) - [播客总结](https://linkdigest.dev/zh/boke-zongjie) - [抖音视频转文字](https://linkdigest.dev/zh/douyin-shipin-zhuanwenzi) - [公众号文章总结](https://linkdigest.dev/zh/gongzhonghao-wenzhang-zongjie) - [公众号文章导出](https://linkdigest.dev/zh/gongzhonghao-wenzhang-daochu) - [B站视频笔记](https://linkdigest.dev/zh/bilibili-shipin-biji) - [剪映识别字幕收费了怎么办](https://linkdigest.dev/zh/jianying-zimu-shoufei) - [轻抖文案提取有网页版吗](https://linkdigest.dev/zh/qingdou-wenan-tiqu-tidai) - [NotebookLM 怎么读 B站视频](https://linkdigest.dev/zh/notebooklm-bilibili-shipin) - [如何用元宝总结视频](https://linkdigest.dev/zh/yuanbao-zongjie-shipin) - [如何用 Gemini 总结视频](https://linkdigest.dev/zh/gemini-zongjie-shipin) - [视频总结 skill](https://linkdigest.dev/zh/shipin-zongjie-skill) - [小红书 skill](https://linkdigest.dev/zh/xiaohongshu-skill) - [抖音 skill](https://linkdigest.dev/zh/douyin-skill) - [B站视频生成思维导图](https://linkdigest.dev/zh/bilibili-siwei-daotu) - [B站视频总结插件](https://linkdigest.dev/zh/bilibili-zongjie-chajian) - [小红书笔记导出](https://linkdigest.dev/zh/xiaohongshu-biji-daochu) - [苹果播客字幕](https://linkdigest.dev/zh/pingguo-boke-zimu) - [播客链接转文字](https://linkdigest.dev/zh/boke-lianjie-zhuanwenzi) - [一小时视频转文字](https://linkdigest.dev/zh/yixiaoshi-shipin-zhuanwenzi) - [长视频总结 AI](https://linkdigest.dev/zh/changshipin-zongjie) - [账号体检](https://linkdigest.dev/zh/zhanghao-tijian) - [小红书选题](https://linkdigest.dev/zh/xiaohongshu-xuanti) - [爆款笔记怎么找](https://linkdigest.dev/zh/xiaohongshu-baokuan-biji-zenme-zhao) - [小红书仿写](https://linkdigest.dev/zh/xiaohongshu-fangxie) - [抖音口播文案怎么写](https://linkdigest.dev/zh/douyin-koubo-wenan-zenme-xie) - [MediaCrawler 替代](https://linkdigest.dev/zh/mediacrawler-tidai) - [Jina / Firecrawl 读不了小红书](https://linkdigest.dev/zh/jina-firecrawl-xiaohongshu) - [链接读取实测](https://linkdigest.dev/zh/lianjie-duqu-ceping) - [红果短剧题材](https://linkdigest.dev/zh/hongguo-duanju-ticai) - [红果短剧 API](https://linkdigest.dev/zh/hongguo-duanju-api) - [微博 API](https://linkdigest.dev/zh/weibo-api) - [微博视频文案提取](https://linkdigest.dev/zh/weibo-shipin-wenan-tiqu) - [Just One API 对比](https://linkdigest.dev/zh/just-one-api-duibi) - [B站视频转文字](https://linkdigest.dev/zh/bilibili-shipin-zhuanwenzi) - [BibiGPT 对比](https://linkdigest.dev/zh/bibigpt-duibi) - [小红书评论提取](https://linkdigest.dev/zh/xiaohongshu-pinglun-tiqu) - [文案库](https://linkdigest.dev/zh/wenan) - [视频标注 API](https://linkdigest.dev/zh/shipin-biaozhu) - [B站网课转文字](https://linkdigest.dev/zh/bilibili-wangke-zhuanwenzi) - [视频链接转文字](https://linkdigest.dev/zh/shipin-lianjie-zhuanwenzi) - [视频文案提取](https://linkdigest.dev/zh/shipin-wenan-tiqu) - [AI 总结视频](https://linkdigest.dev/zh/ai-shipin-zongjie) - [双十一口碑雷达](https://linkdigest.dev/zh/shuang11) - [痛点雷达](https://linkdigest.dev/zh/tongdian-leida) - [出海痛点雷达](https://linkdigest.dev/zh/chuhai-tongdian) - [用户痛点分析](https://linkdigest.dev/zh/yonghu-tongdian-fenxi) - [小红书评论分析](https://linkdigest.dev/zh/xiaohongshu-pinglun-fenxi) - [竞品口碑分析](https://linkdigest.dev/zh/jingpin-koubei-fenxi) - [TikTok 选品痛点](https://linkdigest.dev/zh/tiktok-xuanpin-tongdian) - [DeepSeek 分析视频链接](https://linkdigest.dev/zh/deepseek-fenxi-shipin-lianjie) - [豆包总结视频内容](https://linkdigest.dev/zh/doubao-zongjie-shipin) - [Kimi 链接无法打开](https://linkdigest.dev/zh/kimi-lianjie-wufa-dakai) - [AI 读不了抖音链接](https://linkdigest.dev/zh/ai-du-bu-liao-douyin-lianjie) - [数据来源与合规](https://linkdigest.dev/zh/shuju-laiyuan) Japanese pages (written for Japanese teams working with the Chinese market — inbound tourism, cross-border e-commerce, research, agent developers; not translations): - [ホーム](https://linkdigest.dev/ja) - [小紅書の投稿を日本語で読む](https://linkdigest.dev/ja/xiaohongshu-honyaku) - [小紅書で検索して読む](https://linkdigest.dev/ja/xiaohongshu-kensaku) - [抖音動画の文字起こし](https://linkdigest.dev/ja/douyin-mojiokoshi) - [無料診断](https://linkdigest.dev/ja/shindan) - [公開レポート](https://linkdigest.dev/ja/report) - [API ドキュメント](https://linkdigest.dev/ja/docs) - [小紅書とは](https://linkdigest.dev/ja/xiaohongshu-toha) - [口コミの調べ方](https://linkdigest.dev/ja/xiaohongshu-kuchikomi-shirabekata) - [翻訳ツールの選び方](https://linkdigest.dev/ja/xiaohongshu-honyaku-tool) - [訪日中国人の口コミ分析](https://linkdigest.dev/ja/inbound-kuchikomi-bunseki) - [運用代行の費用相場](https://linkdigest.dev/ja/xiaohongshu-unyou-daikou-hiyou) - [分析ツールの選び方](https://linkdigest.dev/ja/chugoku-sns-bunseki-tool) 红果短剧 (2026-11-15): a drama page link (hongguoduanju.com/detail?series_id=…) reads as the drama — synopsis, tags, episode count, score and raters, likes, saves, heat, rank label and the top viewer reviews (insight works on them). Episodes are never read by our server (the site's robots.txt disallows its players): an episode link is answered, not charged, with the route — play it in your own browser and press the extension's "Digest this video". What is winning on the rankings, counted from 48 dramas and the reviews of 24: https://linkdigest.dev/hongguo-short-drama-trends (English) · https://linkdigest.dev/zh/hongguo-duanju-ticai (中文) · skill hongguo-drama-research. Benchmark (2026-11-14, reproducible): 24 links sampled by rule before any reader ran (Bilibili popular list; Douyin, Xiaohongshu and YouTube topic searches, 6 each), read by LinkDigest, Jina Reader, a plain fetch and yt-dlp. LinkDigest got content on 23/24 (speech 16, text in picture 22, comments 6; one 3-hour YouTube video came back title-only); Jina Reader opened 14/24 posts (Xiaohongshu 0/6), the plain fetch 7/24, yt-dlp 12/24, and none of the three got speech or picture text. Page: https://linkdigest.dev/zh/lianjie-duqu-ceping · scripts and per-link scores: https://github.com/jcaiagent7143-ui/linkdigest-mcp/tree/main/benchmark Comparisons (competitor rows dated on the page): - [LinkDigest vs Supadata](https://linkdigest.dev/compare/linkdigest-vs-supadata) - [The link Firecrawl can't read](https://linkdigest.dev/compare/linkdigest-vs-firecrawl-jina-for-xiaohongshu) - [LinkDigest vs MediaCrawler](https://linkdigest.dev/compare/linkdigest-vs-mediacrawler) - [LinkDigest vs Just One API](https://linkdigest.dev/compare/linkdigest-vs-just-one-api) - [LinkDigest vs TikHub](https://linkdigest.dev/compare/linkdigest-vs-tikhub) - [LinkDigest vs BibiGPT](https://linkdigest.dev/compare/linkdigest-vs-bibigpt) - [LinkDigest vs xiaohongshu-mcp](https://linkdigest.dev/compare/linkdigest-vs-xiaohongshu-mcp)