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. The result depends on your source recording and selected settings.
Hello, thank you for watching.1
00:00:00,000 --> 00:00:03,000
Hello, thank you for watching.
WEBVTT
00:00:00.000 --> 00:00:03.000
Hello, thank you 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 lecture or recording with a supported codec and close other heavy tabs before retrying.
Before sharing your result
Play the downloaded file and check the transcript, including names and technical terms. Keep your original. Local conversion does not create a public 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.