Upload a recording and get an accurate transcript in minutes — with timestamps, 99 languages and TXT, SRT or VTT export. No account needed to start.
1. Drop an audio or video file into the box above — MP3, WAV, M4A, MP4, MOV and WEBM all work. 2. Leave the language on Auto-detect or pick it. 3. The transcript appears as it's processed; fix any word by clicking it, then download TXT, SRT or VTT.
Transcription runs on OpenAI's Whisper large-v3-turbo model, which handles accents, background noise and 99 languages well. The file is processed in short pieces, so text starts appearing right away instead of after the whole file.
You don't need an account for files up to 10 minutes. We don't add watermarks, don't hide the text behind a paywall, and don't store your recording.
Yes. Without an account you can transcribe files up to 10 minutes, 3 files a day. A free account raises that to 60 minutes a day and 30-minute files; paid plans go up to 60-minute files.
Very accurate for clear speech. Heavy background noise, people talking over each other and unusual jargon or names lower it — you can fix any line before exporting.
99 languages, detected automatically. You can also translate the speech to English as it's transcribed.
No. Your file is converted in your browser and sent in short pieces for transcription; we don't store the audio or the text. Download your transcript before closing the page.