Common questions about how Voice to Text works, what it costs, and how your data is handled.
Yes — it's completely free, with no account, no subscription, and no hidden limits on live recording or file transcription.
Live "Start Listening" transcription needs a Chromium-based browser (Chrome or Edge) because it relies on the Web Speech API, which Firefox and Safari only support partially or not at all. Uploading a file for "Transcribe File" works in any modern browser, since that's processed on the server.
No transcript or audio is stored on the server. Live recording is processed by your browser's own speech engine; uploaded files are transcribed on the server and the temporary copy is deleted immediately afterward. See the Privacy Policy for details.
It depends on audio quality, accent, background noise, and language — automated speech recognition isn't perfect. Don't rely on it for anything high-stakes, like medical, legal, or safety-critical use, without double-checking.
50+ languages, plus several mixed auto-detect pairings (for example Hindi+English or Spanish+English) for code-switching speech. Pick one from the Language dropdown before you start.
Yes — switch to the "Upload Audio" tab, drop in an MP3, WAV, M4A, OGG, or WebM file, and click "Transcribe File" to have the server transcribe it.
It keeps going continuously — the app automatically restarts the recognition session in the background whenever the browser's speech engine times out on its own, so you don't have to keep clicking Start.
Yes — after you stop, click "Save Recording" to download what you recorded as a WAV file.
No accounts at all. Everything — transcripts, sessions, and settings — is saved locally in your own browser.
Your current transcript, saved sessions, bookmarks, and settings stay in your browser's local storage and will still be there next time you open the app — nothing is lost unless you clear your browser data or use the app's own Clear / Clear All buttons.
Yes, the output is a normal editable text box — type directly into it, and use Undo/Redo (Ctrl+Z / Ctrl+Y) if needed.
Plain text (.txt), subtitles (.srt), Markdown (.md), CSV, JSON, or Word (.docx) — pick one from the Download menu.
That depends on where you are — many places require the consent of some or all parties before a conversation can be recorded. You're responsible for complying with your local recording and consent laws; see the Terms of Service for more.
Yes — the app is responsive, and you can scan the QR code button on desktop to quickly open the same app on your phone and use its microphone.