Get a RedNote transcript
Paste a RedNote (Xiaohongshu) video URL above and the spoken audio comes back as timestamped text. RedNote is photo-carousel-first with video as a secondary format, and its caption tooling is noticeably less mature than on video-first platforms — a real, extractable caption track is the exception rather than the norm.
Audio on the platform is overwhelmingly Mandarin, and the creator tooling is built Chinese-first. The transcript comes back in that source language: this transcribes accurately, but it does not translate, so a Mandarin video produces Mandarin text. Videos are short — generally under three minutes, closer to Reels than to Bilibili — so transcripts come back quickly and are short enough to work with directly.
- Works where no extractable caption track exists, which on RedNote is most of the time.
- Transcribes Mandarin audio in Mandarin; it does not translate to another language.
- Short-form video, so a transcript is usually a single readable pass.
- Markdown or TXT export for repurposing a post into writing elsewhere.
Captions on RedNote, as they actually are
RedNote (Xiaohongshu) is a photo-carousel-first platform with video as a secondary format, and caption tooling on it is noticeably less mature than on video-first platforms — real, extractable caption tracks are the exception, not the norm.
- Typical length
- Short vertical video, generally under 3 minutes, closer to Reels/TikTok than to YouTube or Bilibili.
- URL shape
- xiaohongshu.com/explore/...
What you're doing with the transcript
The export format and the workflow both depend on what the text is for. These go into detail for RedNote specifically:
- Turn a RedNote (Xiaohongshu) video into usable text
Turning one video into a blog post, thread, or newsletter section without rewriting it from memory.
- RedNote (Xiaohongshu) video to SRT subtitles
Turning a transcript into a subtitle file for an editor or a web player.
FAQ
Other platforms
The free tier includes 15 minutes of video a month, transcripts in the language spoken, and TXT/SRT/VTT/Markdown/JSON export — enough to run a RedNote video through and judge the output before committing to anything.