Transcribe audio to text
Use your browser's speech recognition to convert audio or video into SRT, VTT, or plain text. Real-time, private, free.
How to Use
- Choose the spoken language of your audio.
- Select an audio or video file (up to 100MB).
- The audio plays once while the browser transcribes it in real time.
- Download the transcript as SRT, VTT, or plain text.
All processing is done in your browser, and files are never sent to a server.
Frequently Asked Questions
In your browser, through the built-in Web Speech API. Some implementations may use cloud recognition (browser-dependent). Files are not uploaded by ConvertBox.
The Web Speech API listens to your device's audio output as the file plays. Mute the speakers if you prefer β the recognition still works.
Accuracy is best on clear single-speaker recordings. Background noise, accents, and overlapping speech reduce quality.