Video to text
Transcribe a video’s speech into text and timed JSON.
No files selected
Accepted files: .wav,.mp3,.m4a,.flac,.mp4,.mov,.webm. Choose one file. Up to 20 MiB in total.
Runs with local model weights on this website’s server. No external AI API is used. Review the result for errors. Local Whisper tiny. Clips up to five minutes; review words and timing. Up to 1,000,000 characters. Review the settings before running.
Your result
How to use Video to text
- Choose a file in WAV, MP3, M4A, FLAC, MP4, MOV or WEBM.
- Review the settings, then choose Convert file.
- Review the result, then use Copy result or a download link when available.
Useful next steps
What to expect
Transcribe a video’s speech into text and timed JSON. Runs with local model weights on this website’s server. No external AI API is used. Review the result for errors. Local Whisper tiny. Clips up to five minutes; review words and timing.