Upload a voice memo, interview, lecture, podcast, or meeting recording and get a timestamped transcript back. The spoken language is detected automatically, and you can copy the words or export TXT, SRT, and VTT files.
Upload an audio or video recording you have permission to process.
Drop an MP3, M4A, WAV, OGG, WEBM, MP4, or MOV file up to 60 minutes long that you own or have permission to process.
Auto-detect handles most recordings. Choose the spoken language yourself when a file mixes accents or starts with music.
Read the timestamped transcript in the browser, copy it, or download TXT for notes and SRT or VTT for subtitles.
Typing up an interview or a lecture by hand takes several times longer than the recording itself. Uploading the audio file gives you a full draft in minutes, with timestamps attached to every line. You can then correct names and jargon, pull quotes, or search the text for the moment you need instead of scrubbing through the recording again.
A transcript turns a voice memo into notes, a podcast episode into a blog post draft, and a meeting into searchable minutes. Because timing is preserved, the same result also becomes an SRT or VTT subtitle file for a video edit. If you want to turn the words into a new video, the transcript is a ready-made starting script.
MP3, M4A, WAV, OGG, and WEBM audio files work, and so do MP4 and MOV videos. The audio track is extracted and transcribed for you.
Recordings up to 60 minutes and 500 MB are supported. Split longer recordings into parts and transcribe each one separately.
The spoken language is detected automatically. English, Spanish, Portuguese, German, French, Italian, Japanese, Korean, and dozens of other languages are supported, and you can pick the language manually when detection guesses wrong.
Yes. Every transcript keeps its timestamps, so you can download an SRT or VTT subtitle file as well as plain TXT text.
Yes. Create a free account before uploading, and you will come straight back to this page to add your file and start the transcript.