Transcribe Audio and Video to Text
Turn speech into text: interviews, meetings, lectures, voice notes, podcasts and videos. Fix any line, then copy the text or download it as plain text or with timestamps. The speech recognition runs in your browser, so your recording is never uploaded.
How to transcribe audio
- 1Click “Choose audio or video” or drag a file onto the page.
- 2Pick Fast or More accurate and the spoken language (or let it detect it), then click “Transcribe”.
- 3Fix any line if needed, then copy the text or download TXT, SRT or VTT.
Powered by Whisper
Transcription uses OpenAI's Whisper speech recognition model running on your own device. “Fast” downloads about 80 MB once; “More accurate” about 250 MB. After that the model is cached by your browser.
Formats
Download plain text, text with timestamps, or SRT and VTT subtitle files with timing for every line, ready for YouTube and video editors.
Languages
Choose from around two dozen common languages, including English, Hindi, Spanish, Portuguese, French, German, Arabic and Japanese, or let the language be detected automatically.
Frequently asked questions
- Is it free?
- Yes, with no signup and no limits on length beyond your device's memory.
- Is my recording uploaded?
- No. The AI runs in your browser and the audio stays on your device.
- How accurate is it?
- Clear speech in a quiet room transcribes very well. Heavy background noise, music and overlapping speakers lower accuracy; try “More accurate” or clean the audio first with the Noise Remover.
- Does it tell speakers apart?
- No. The transcript is a single stream of text with timestamps.
- Can I transcribe a video?
- Yes. Choose the video and its soundtrack is transcribed.