Audio & video to text

Transcribe audio & video — free & private

Turn interviews, meetings, voice notes, podcasts and lectures into text using OpenAI Whisper — running entirely in your browser. 100+ languages, timestamps, and SRT/VTT subtitle export. Unlike Otter, Rev or Descript, your recording is never uploaded and there are no per-minute fees or limits. The AI model downloads once and is cached.

Audio sourceupload a file or record straight from your microphone

or drop an audio or video file here — mp3, wav, m4a, mp4…

Transcribe audio or video to textInterviews, meetings, voice notes, podcasts, lectures — 100+ languages, timestamps, SRT/VTT subtitles. Runs entirely on your device; nothing is uploaded.

Model & languagebigger models are more accurate and slower

Model

Better accuracy · 100+ languages · ~80 MBLanguageAuto-detect works well on clear speech.Task

Timestamps

Segments are required for SRT / VTT subtitles.

Choose or record some audio first.

Powered by OpenAI Whisper running in your browser (transformers.js). Your audio is never uploaded, with no per-minute fees or limits.