Upload your audio file
Drop in an MP3, WAV, M4A, FLAC or OGG recording. It goes directly to an identity-scoped, private storage path — not through a web server.
AI speech to text, free to start
Convert audio to text online with AI speech recognition — no account needed. Upload an MP3, WAV, M4A, FLAC or OGG file and get a clean transcript back. Your first 60 seconds of transcription are free, then it is a simple $1 per minute.
How it works
Drop in an MP3, WAV, M4A, FLAC or OGG recording. It goes directly to an identity-scoped, private storage path — not through a web server.
We inspect duration on the server, then convert speech to text automatically. Up to 60 seconds is free; longer files are rounded to the nearest minute.
Transcription runs asynchronously. Copy your text or download the transcript as private TXT and JSON files.
One tool, every recording
One speech to text converter for every kind of audio recording — interviews, meetings, lectures, podcasts, calls and voice memos.
Transcribe an audio file to text in a couple of clicks. MP3 transcription, WAV, M4A, FLAC and OGG all work exactly the same way, with free AI transcription for the first 60 seconds.
Turn a voice memo, dictation or recorded call into text. Auto transcribe a recording instead of typing it out by hand.
Pick the spoken language before you upload, or let automatic detection choose it — American English, British English, Spanish, French, German, Japanese, Arabic and many more.
Refreshingly simple
No plan, no credits, no renewal surprises. Transcribe audio to text free for every recording of 60 seconds or less; longer recordings are billed by the minute.
Good to know
Upload your recording and the AI audio to text transcription starts on its own. There is nothing to install and no account to create — readable text comes back in the browser.
MP3, WAV, M4A, FLAC and OGG recordings up to the configured upload limit.
Yes — free online transcription for every recording of 60 seconds or less, with no card and no sign-up. Longer recordings cost $1 per minute.
Paid recordings are rounded to the nearest whole minute, with at least one billable minute. The free 60 seconds are not deducted.
117 languages and regional variants, from American English and Spanish to Japanese and Arabic. Choose one before uploading, or let automatic language detection pick it.
No. Audio and transcripts use private paths isolated to this browser or your account. You may delete both from the result page.
Free files begin after analysis. Paid files begin only when the signed payment webhook is verified — not from a redirect.