Video to Text
Transcribe speech from a local video in your browser. Edit the transcript, copy it or export TXT, SRT and VTT.
Select the language spoken in the video; it is independent of the page language.
First use downloads an AI speech model. Keep this tab open; speed depends on your device. Model files download from Hugging Face, a third-party service, and may be cached by your browser. First use needs internet; mobile devices may take longer.
Video and audio stay on your device; they are not uploaded.
First use downloads an AI speech model. Keep this tab open; speed depends on your device. Model files download from Hugging Face, a third-party service, and may be cached by your browser. First use needs internet; mobile devices may take longer.
Review the result: accuracy is not guaranteed. Speaker identification is not supported.
Turn video into text in three steps
- 1
Choose video
Choose a local video with speech.
- 2
Transcribe video
Choose the spoken language, then start local AI transcription.
- 3
Download TXT
Review and edit the text, then copy or download it.
Ways to use your transcript
- Create a draft of subtitles.
- Turn a lesson into study notes.
- Prepare a searchable interview transcript.
Output examples
These examples show the output format. Your result depends on the source file and selected settings.
Hello, thanks for watching.1
00:00:00,000 --> 00:00:03,000
Hello, thanks for watching.
WEBVTT
00:00:00.000 --> 00:00:03.000
Hello, thanks for watching.
Edit each segment. Subtitle timestamps are preserved.
If processing fails
- The audio could not be decoded. The codec may be unsupported or the file may have no audio.
- The speech model could not load. Check your connection and try again.
- Review the result: accuracy is not guaranteed. Speaker identification is not supported.
Keep this tab open. Try a shorter file with a supported codec and close other heavy tabs before retrying.
Before sharing the result
Play the downloaded file and review any transcript. Keep your original. Local conversion does not publish a sharing link.
Frequently asked questions
Is my video uploaded?
Video and audio stay on your device; they are not uploaded. First use downloads an AI speech model. Keep this tab open; speed depends on your device. Model files download from Hugging Face, a third-party service, and may be cached by your browser. First use needs internet; mobile devices may take longer.
Which videos are supported?
One MP4, MOV or WebM file, up to 100 MB and 5 minutes. The audio codec must be supported by your browser.
Which language should I choose?
Select the language spoken in the video; it is independent of the page language.
How accurate is the transcript?
Review the result: accuracy is not guaranteed. Speaker identification is not supported.