coverage

6 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 backNotes
xiaohongshu 小红书liveCaption, tags, every image described, on-screen text.Image notes and video notes. No login needed.
douyin 抖音liveTranscript with timecodes, sampled frames, on-screen text.Video posts and image notes, including 图文.
youtubeliveNative captions where published, otherwise a watched transcript.Read by Gemini watching the video, since YouTube blocks datacenter IPs.
tiktokliveTranscript with timecodes, sampled frames, on-screen text.Short links resolve. Rate-limits under load.
xlivePost text, image descriptions, transcript when there is video.Posts with video or images.
web pagesliveReadable article text, title, author, publish date.Article text and metadata.
bilibiliblockedNothing yet — the request never reaches the post.Bilibili refuses our server's address (HTTP 412). Needs a proxy.
instagramsoonNot yet measured.Wired, not yet verified end to end.

every digest

The same shape, whatever the source

One schema across all 6 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

Three digests free, no card. If a link on a live platform does not work, that is a bug worth hearing about.