Xiaohongshu speech and subtitle extraction
Xiaohongshu Video Subtitle Extractor
A Xiaohongshu note title or description may not contain the full spoken content. Videosays turns publicly accessible Xiaohongshu video links into clean text and timestamped subtitles.
Use cases for Xiaohongshu subtitle extractor
Capture spoken content from creator videos
Review hooks, offers, and content structure
Prepare a timestamped subtitle draft
Write video content into a research library
Extract content from a Xiaohongshu video link
Submit a public link and Videosays creates a transcription task while retaining useful context such as title, author, platform, and duration.
Choose text or timeline output
Clean text works well for reading and analysis, while timestamped output helps with navigation, proofreading, and SRT or VTT subtitle files.
Continue in an agent workflow
Pass the transcript to an AI agent for summaries, tags, offer extraction, or competitor research through the Skill, CLI, or API.
FAQ
Does this work with image-only Xiaohongshu notes?
Subtitle extraction is intended for video notes with spoken audio. Image-only notes do not contain video speech to transcribe.
What if the video has no existing subtitles?
Videosays may still generate text when accessible audio content is available.
Which export formats are supported?
Completed tasks support clean text and TXT, SRT, or VTT output.