Convert Audio and Video to Text

Upload MP3, MP4, WAV, or other audio/video files. Whisper transcribes them with timestamps in seconds.

Upload a fileNo credit card required

How it works

  1. 1

    Upload a file

    Drag and drop your audio or video.

  2. 2

    Whisper transcribes

    OpenAI Whisper recognizes the speech and converts it to text in 50+ languages.

  3. 3

    Download as TXT/SRT/VTT

    Get the timestamped transcript or jump into AI chat with it.

Supported file types

  • MP3, WAV, M4A, AAC (audio)
  • MP4, MOV, WEBM (video)
  • Files up to 50 MB
  • Meeting recordings, podcasts, interviews
  • Conference and lecture recordings

Example output

Inputweekly-product-meeting.mp3 (28:14 duration)
Transcript (timestamped)
[00:00] Today we'll review the Q2 roadmap.
[02:15] Our goal is to raise mobile conversion from 18% to 25%.
[08:42] A/B test results are still inconclusive...
[21:05] Decision: cut mobile onboarding to 2 screens.

Who is this for?

Meeting notes

Turn Zoom/Teams recordings into transcripts, surface action items.

Journalists

Auto-transcribe interviews, search for quotable lines.

Podcast producers

Produce episode transcripts for blog posts or subtitles.

Students

Convert lecture recordings into searchable notes.

Frequently asked questions

Turn audio into text

Whisper-powered accuracy. Start with the Free plan.

Try free

More Tools