LinkDigest — Xiaohongshu, Douyin, TikTok, YouTube to text

Quality 75 / 100good

5 tools, about 1,847 tokens to load them all · tool set 4da6aa27eb6f · tools last changed 2026-10-17 · checked 2026-10-19 10:20 UTC

Tool changes

• 2026-10-17search_linkschangeddescription, input schema
  before

  Find posts on a topic on youtube, x, web (web search scoped to the platform, filtered to links digest_url can read). Free: no credits, 10 searches an hour per key. Returns a numbered list; pass digest: true to read them as one batch and compare them (then compare_links with the batch_id). xiaohongshu and douyin cannot be searched from a server — their search needs a logged-in session — so for those the user opens the search in their own browser and presses the extension's “Digest the notes on this page” button; then list_batches. Needs an API key. Example: query="护肤 早C晚A", platform="youtube", limit=5.

  after · 75% of words in common

  Find posts on a topic on xiaohongshu, youtube, x, web (web search scoped to the platform, filtered to links digest_url can read). Free: no credits, 10 searches an hour per key. Returns a numbered list; pass digest: true to read them as one batch and compare them (then compare_links with the batch_id). xiaohongshu returns the notes the web has indexed, read from their public pages (no login, no session); for the user's own feed or a search the web has not seen, they press the extension's “Digest the notes on this page” button on the page they see, then list_batches. douyin cannot be searched from a server and its links refuse every automated read: the user plays a video in their own tab and presses “Digest this tab”. Needs an API key. Example: query="护肤 早C晚A", platform="xiaohongshu", limit=5.

• 2026-10-17list_batcheschangedinput schema
• 2026-10-17search_linksadded

  Find posts on a topic on youtube, x, web (web search scoped to the platform, filtered to links digest_url can read). Free: no credits, 10 searches an hour per key. Returns a numbered list; pass digest: true to read them as one batch and compare them (then compare_links with the batch_id). xiaohongshu and douyin cannot be searched from a server — their search needs a logged-in session — so for those the user opens the search in their own browser and presses the extension's “Digest the notes on this page” button; then list_batches. Needs an API key. Example: query="护肤 早C晚A", platform="youtube", limit=5.

• 2026-10-17list_batchesadded

  The last batches on this API key, newest first — including the ones the browser extension's “Digest the notes on this page” button started from the user's own Xiaohongshu or Douyin tab. Each line: batch_id, label, created, status done/total, credits, synthesis (ready, pending, failed or none). Pass a batch_id to compare_links to read the comparison. Starts nothing, costs nothing. Needs an API key.

• 2026-10-17compare_linkschangeddescription
  before

  Read a set of Xiaohongshu, Douyin, TikTok, YouTube or X links as one batch and write one comparison over them (批量综合): the themes, hooks, formats and claims they share, the objections readers raise and the gaps none of them cover, every example naming which link it came from and checked against it word for word. The first call starts the batch and returns a batch id; call again with batch_id to collect. Needs an API key. Each link is read at its usual price (cached links are free); the comparison is 1 credit per 10 links. Example: urls=["https://xhslink.com/o/a", "https://xhslink.com/o/b"].

  after · 84% of words in common

  Read a set of Xiaohongshu, Douyin, TikTok, YouTube or X links as one batch and write one comparison over them (批量综合): the themes, hooks, formats and claims they share, the objections readers raise and the gaps none of them cover, every example naming which link it came from and checked against it word for word. The first call starts the batch and returns a batch id; call again with batch_id to collect. Needs an API key. Each link is read at its usual price (cached links are free); the comparison is 1 credit per 10 links. Example: urls=["https://xhslink.com/o/a", "https://xhslink.com/o/b"]. After the browser extension's “Digest the notes on this page” button, call list_batches and pass the newest batch_id here.

• 2026-10-17compare_linksadded

  Read a set of Xiaohongshu, Douyin, TikTok, YouTube or X links as one batch and write one comparison over them (批量综合): the themes, hooks, formats and claims they share, the objections readers raise and the gaps none of them cover, every example naming which link it came from and checked against it word for word. The first call starts the batch and returns a batch id; call again with batch_id to collect. Needs an API key. Each link is read at its usual price (cached links are free); the comparison is 1 credit per 10 links. Example: urls=["https://xhslink.com/o/a", "https://xhslink.com/o/b"].

• 2026-10-17digest_urlchangedinput schema
• 2026-10-08digest_urlchangeddescription, input schemameaning changed
  before

  Turn a social media URL into LLM-ready context. Works on Xiaohongshu, Douyin, TikTok, YouTube, X and ordinary web pages. Returns the post's transcript, on-screen text, image descriptions, caption and metadata — the things you cannot get by fetching the URL yourself, because these posts are video or images behind tokenised share links. Use this whenever you are given a social media link. Bilibili, Instagram and Facebook are not supported. Works without an API key for a first look: a summary (title, author, key points, counts), up to two a day per address; the full transcript, per-image text and receipt need a key (free credits on sign-up — see check_balance). A long video may not finish in one call: if the result names a job id, call this tool again with that job_id (and no url) to collect it. Set breakdown to true to also get a teardown of how the post is built (hook, timed beats, reusable template) — useful when the user wants to learn from or remake a post. For a long video (a talk, a course, a podcast), set depth to transcript: the whole transcript with a frame a minute, at about half the per-minute price. A digest says how much of the post it captured and what it did not read (a Coverage section in markdown; `coverage` in json), and backs each key point with a short quote the server checked against the post (`key_point_support` in json, verified true or false).

  after · 42% of words in common

  Read what a social media link actually says. Works on Xiaohongshu, Douyin, TikTok, YouTube, X and ordinary web pages. Returns the post's transcript with times, on-screen text, the text in every image, caption and counts, key points each backed by a quote checked against the post (`key_point_support` in json), and a receipt of what was read (`coverage` in json). Bilibili, Instagram and Facebook are not supported. Works without an API key for a first look (a summary, two a day per address); the full output needs a key — see check_balance. If the result names a job id, call again with job_id only. Example: url="https://v.douyin.com/abc/", ask="推荐了什么产品、多少钱？".

• 2026-10-07check_balanceadded

  How many credits this API key has left, what each kind of read costs, and where to buy more (links need no sign-in; the credit pack takes Alipay). Without a key it returns the prices and how to get a key. Call it before a batch of reads, or when digest_url says credits ran out.

• 2026-10-07digest_urlchangeddescription
  before

  Turn a social media URL into LLM-ready context. Works on Xiaohongshu, Douyin, TikTok, YouTube, X and ordinary web pages. Returns the post's transcript, on-screen text, image descriptions, caption and metadata — the things you cannot get by fetching the URL yourself, because these posts are video or images behind tokenised share links. Use this whenever you are given a social media link. Bilibili, Instagram and Facebook are not supported. A long video may not finish in one call: if the result names a job id, call this tool again with that job_id (and no url) to collect it. Set breakdown to true to also get a teardown of how the post is built (hook, timed beats, reusable template) — useful when the user wants to learn from or remake a post. For a long video (a talk, a course, a podcast), set depth to transcript: the whole transcript with a frame a minute, at about half the per-minute price. A digest says how much of the post it captured and what it did not read (a Coverage section in markdown; `coverage` in json), and backs each key point with a short quote the server checked against the post (`key_point_support` in json, verified true or false).

  after · 85% of words in common

  Turn a social media URL into LLM-ready context. Works on Xiaohongshu, Douyin, TikTok, YouTube, X and ordinary web pages. Returns the post's transcript, on-screen text, image descriptions, caption and metadata — the things you cannot get by fetching the URL yourself, because these posts are video or images behind tokenised share links. Use this whenever you are given a social media link. Bilibili, Instagram and Facebook are not supported. Works without an API key for a first look: a summary (title, author, key points, counts), up to two a day per address; the full transcript, per-image text and receipt need a key (free credits on sign-up — see check_balance). A long video may not finish in one call: if the result names a job id, call this tool again with that job_id (and no url) to collect it. Set breakdown to true to also get a teardown of how the post is built (hook, timed beats, reusable template) — useful when the user wants to learn from or remake a post. For a long video (a talk, a course, a podcast), set depth to transcript: the whole transcript with a frame a minute, at about half the per-minute price. A digest says how much of the post it captured and what it did not read (a Coverage section in markdown; `coverage` in json), and backs each key point with a short quote the server checked against the post (`key_point_support` in json, verified true or false).

Showing the latest 10. Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.