Free Voice to Text
Free speech-to-text in your browser: live microphone dictation and audio file transcription with on-device AI. No uploads, no sign-up.
Instant results using the speech engine built into your browser. Note: Chrome/Edge/Safari process the audio via the vendor's cloud service — see the privacy note below.
Transcript
Start recording and your words will appear here.
Drop an audio file here
MP3, WAV, M4A, OGG, FLAC, WebM — decoded and transcribed on this device, up to 90 minutes
Privacy — how your audio is handled
- Nothing is uploaded to may.tools. There is no server-side processing: recordings, audio files and transcripts stay in your browser, and downloads are generated locally on your device.
- Browser engine (live): the instant live mode uses the speech engine built into your browser (Chrome, Edge, Safari). Those browsers process audio through the vendor's own cloud service (e.g. Google's) — that is the browser's built-in behavior, and the reason the fully local engine below exists. The recorded audio itself never leaves your device either way.
- On-device Whisper (live & audio files): audio-file transcription and the on-device live engine run the open-source Whisper model locally in your browser via WebAssembly / WebGPU. The model file downloads once from a public CDN (Hugging Face or its mirror hf-mirror.com) and is then cached by your browser for offline use. No audio is ever sent anywhere in this mode.