Xiaohongshu video to text: the transcript from the platform's own subtitles (2026)
1 endpoint does it, with no speech recognition of your own: Xiaohongshu makes Chinese subtitles for its videos, and xiaohongshu.videos.get returns the subtitle file's address (ext.subtitle_url, SRT) with the video at $0.0200 a call. Download it and drop the timings: that is the transcript. DataXAPI reads Xiaohongshu (RedNote) with 23 endpoints, from $0.0200 a call; a failed call is not charged, and the free trial covers up to 333 calls.
1. Call xiaohongshu.videos.get with the note's link and view: "full".
2. Download the SRT file ext.subtitle_url points to: one line a passage, with start and end times.
3. Drop the numbers and timings and join the lines: that is the full text. Keep the timings to quote by time.
Worth knowing
The subtitles are the platform's own, made automatically: a strong accent or loud music can bring wrong words. Where the platform made none, ext.subtitle_url is empty, and only the video file (ext.video_url) is there to transcribe yourself.
In bulk: find video notes by keyword with xiaohongshu.notes.search, or list a creator's with xiaohongshu.users.notes.list, then get each one's subtitles.
How do I use it from an AI?
Once connected, say “get the subtitles of this creator's last 10 video notes and sum each up in three sentences”.
To connect: paste this to your AI assistant: “Read https://dataxapi.com/agents.md and set up DataXAPI here. My API key is dx_…; use it for every DataXAPI call.” A client that takes a remote MCP server can be given https://api.dataxapi.com/mcp with the header Authorization: Bearer <key> instead.
Why DataXAPI
Steady: endpoints were available 99.9% of the last 30 days, on a public status page you can check.
Fast: a paid call took 1.3 seconds at the median over the last 7 days (counted 2026-11-06).
Fewer tokens: across 21 endpoints on Xiaohongshu (RedNote), one recorded real response each, the platform's own JSON comes to 480k tokens and what an AI reads through DataXAPI's MCP server to 36k, 92% fewer; the JSON of a direct API call is 85% fewer too (counted 2026-11-06). Every platform answers in one shape: the author in author, counts in metrics, the next page in page.next_cursor, so another platform needs no new parser.
See before you pay: every endpoint's page shows a recorded real response, field by field.
Spending you control: a failed call is not charged; each key can have a limit, X-Max-Price caps one call, and the same Idempotency-Key within 24 hours is never charged twice.
Ready for AI: a remote MCP server listed in the official MCP registry as com.dataxapi/mcp, usable from Claude, Cursor and ChatGPT.
Free trial of up to 333 calls, no card.
Endpoints
Each with its price; every page has the parameters, the fields and a recorded response.