Voice to Text
Transcribe audio or voice recordings to text with AI (Whisper) running entirely in your browser. Upload MP3, WAV, M4A or even video. Nothing is uploaded.
Drag & drop files here
or
Choose filesProcessed on your device. Nothing is uploaded
Or record directly. Audio never leaves this device.
How to Voice to Text
- 01Add your files
Click “Choose Files” or drag and drop them onto the page. Batch conversion is supported.
- 02Adjust settings
Pick quality, size or other options. Sensible defaults are pre-selected.
- 03Convert & download
Hit Convert and download your files. Everything runs locally. Nothing is uploaded.
Frequently asked questions
How do I transcribe audio to text?
Drop an audio or video file, pick a language (or auto-detect) and hit Convert. The Whisper AI model transcribes it locally on your device and you download the text.
Is my audio uploaded?
No. The AI model comes to your audio, not the other way around. Everything is processed in your browser. Ideal for private recordings, interviews and meetings.
Which model is used?
OpenAI's Whisper, compiled to run in-browser. The Fast model (~150 MB) is best for most use; the More accurate model (~290 MB) handles difficult audio better.
Can I get timestamps?
Yes. Enable the timestamps option to download an SRT subtitle file instead of plain text.