coverage

12 platforms read.
The rest listed honestly.

Every row was checked against a real post, not a doc page. Where something does not work we say so and why, because finding out after you have wired it in is worse than knowing now.

PlatformStateWhat comes backNotesDiscoveryLast verifiedLast 24 hours
xiaohongshu 小红书liveCaption, tags, engagement counts, every image described with the text on it, the share page's top comments, video transcript.Image notes (up to 60 images) and video notes. No login needed.Search API: search_links / POST /api/v1/search, 4 credits a search — the notes the web has indexed, read from their public pages. Your own feed: the extension's “Digest the notes on this page” button on the page you see.2026-11-18 ok100% success
douyin 抖音liveTranscript with timecodes, timed on-screen text, the post's chapters and category.Pasted links read again since 2026-10-21 through Douyin's own embed player. Video and 图文; long videos transcript-first. Anything it will not serve: upload the video saved in the app (保存本地) at /app/upload, or read it from your own tab with the extension.Search API: search_links / POST /api/v1/search with platform douyin, 4 credits a search — the videos the web has indexed (since 2026-10-21). Or paste a link, or the whole share text. For your own feed, the extension reads the tab you are on.2026-11-18 ok100% success
weibo 微博livePost text (emoticons keep their names), author, date, repost / comment / like counts, every photo, the video and how long it is, topic tags, and the post's top comments.Post links read through Weibo's own visitor page — no login. Text, every photo, video, reposts. A post only signed-in followers can see (关注可见 / 好友圈) says so instead of guessing and is not charged; if it carries a video, the extension reads it from your own signed-in tab, the way a Douyin video is read.Paste a link. No search route yet.2026-11-14 ok—
hongguo 红果短剧liveThe drama's synopsis, tags, episode count, rating and how many rated it, likes, saves, heat (热度), the rank label, the filing number (备案号), and its top reviews as comments.A drama's page (hongguoduanju.com/detail?series_id=…) and its series player page (/player/<id>, the address an episode opens at) read from the page's own data: synopsis, tags, episodes, rating, likes / saves / heat, its rank label, filing number and the top written reviews. The episode itself is not read — the player ships its tracks CENC-encrypted, so reading one would mean defeating its content protection. For an episode: play it in your own browser (the web player shows the first few free) and read it with the extension. What is winning right now, counted over 48 ranked dramas: https://linkdigest.dev/hongguo-short-drama-trendsPaste a drama page link. No search route yet.— unknown—
youtubeliveNative captions where published, otherwise a watched transcript.Read by Gemini watching the video, since YouTube blocks datacenter IPs.Search API: search_links / POST /api/v1/search, 1 credit a search, watch and shorts links only.2026-11-15 ok—
tiktokliveTranscript with timecodes, sampled frames, on-screen text.Short links resolve. Speech is read from the video itself, not the sound track.Paste a link. No search route yet.2026-11-15 ok—
xlivePost text, every photo described, transcript and on-screen text when there is video.Video posts in full. Image posts: every photo described. Long-form articles: the lead image.Search API: search_links / POST /api/v1/search, 1 credit a search, status links only.2026-11-18 ok—
wechat 公众号liveFull article text, account name, publish date, every image described with the text on it (up to 60).Public-account articles (mp.weixin.qq.com). No login needed.Paste a link. WeChat search is behind the app.2026-11-17 ok—
web pagesliveReadable article text, title, author, publish date.Article text and metadata.Search API: search_links / POST /api/v1/search with platform web, 1 credit a search.2026-11-18 ok—
bilibililiveTitle, description, uploader, publish date, tags, view / like / comment / coin counts, transcript and sampled frames.Short links (b23.tv) and full video links, read since 2026-10-24 through Bilibili's own embed player — the public page it publishes for other sites. No login needed. A video that is private, deleted or still under review says so and is not charged.Paste a link. No search route yet.2026-11-16 ok—
instagramliveReels: transcript, frames and on-screen text, caption. Photo posts: the full caption, author, hashtags, like and comment counts, and the photo described and read for its text.Reels and video posts are read like any video; photo posts are read from Instagram's own embed page (the one it publishes for other sites), with no login. A carousel gives its first slide; private posts cannot be read.—2026-11-15 ok—
podcast 播客 (小宇宙, Apple Podcasts)liveTranscript with times, show notes, podcast and episode title, publish date, play / comment / like counts and the top comments the 小宇宙 page shows.小宇宙 episode links and Apple Podcasts episode links (…?i=…), read from the public episode page and feed with no login, as text: 1 credit per started 2 minutes, no base credit — a 45-minute episode is 23 credits. Paid episodes cannot be read and are not charged.Paste an episode link. No search route yet.— unknown—
spotifyblocked—Not readable: without a login Spotify's player serves a 30-second preview, and we never use anyone's login. Many shows are also on 小宇宙 or Apple Podcasts — paste that link. A Spotify link is answered with this and not charged.—— unknown—
ximalaya 喜马拉雅soon—Not yet: the public extractor we would read it with is broken upstream. Many of its shows are also on 小宇宙 or Apple Podcasts.—— unknown—

“Discovery” is how posts are found before they are read: a real search API for the open platforms (YouTube, X, the web — search_links, 1 credit a search), your own browser for Xiaohongshu, and the extension from your own tab for Douyin. No login, no cookies, no forged signatures: a platform whose search sits behind a login is never searched from a server, and says so. “Last verified” is the last time a real post on that platform was read in full, by a real request or by the weekly check; degraded means the last read came back thinner than the post, unknown means nothing has read one in the last two weeks. “Last 24 hours” is the share of real requests (ours left out) that came back whole, with failures on our side counted against us; only a failure whose owner we know counts at all (2026-11-06), and the column shows “—” under 3 attempts, because one read is not a rate. The 30-day counts, success rates and median waits are public at GET /api/v1/health/platforms, no key needed.

what you don’t have to do

The parts that are our problem, not yours

Each of these is something that was built, checked against a real link, and is written down in the coverage table or the docs.

No cookies or login for Xiaohongshu.

Image notes and video notes are read with no account at all, so there is nothing of yours to get banned.

Cookie rot is ours.

Douyin's security layer refuses the requests a server signs for itself, so since 2026-10-21 a link is read through Douyin's own embed player — no cookie of ours or yours. A post that player will not serve is refused, not billed.

YouTube read from a datacenter IP.

YouTube blocks datacenter address ranges, so a server-side fetch fails wherever it is deployed. Here a model watches the video instead.

Image notes read in full.

Every image in a Xiaohongshu note is described and read for on-screen text — the 17-image example on the homepage came back with all 17.

degraded names what failed.

A digest that is thinner than the post says so in plain words, in a field your code can branch on, instead of returning a confident description of less.

A digest that read nothing costs nothing.

If no transcript, text or image came back, the digest is not charged and is retried within the hour instead of being cached for a month.

Cached links are free.

Anything anyone has already digested comes back instantly and never counts against you.

every digest

The same shape, whatever the source

One schema across all 12 live platforms, so your prompt does not branch on where the link came from.

always present

platform, author, title, posted_at, caption, key_points and raw_markdown. Empty strings rather than missing keys, so parsing never branches.

when the post has it

transcript with timecodes for anything with speech, ocr_text for on-screen text, and images with a written description of each.

Try one of your own links

10 free credits when you sign up, no card. If a link on a live platform does not work, that is a bug worth hearing about.