Batch transcribe multiple interview files with speaker turns.
Drop one or more interview files
Multiple files supported
Add one or many audio recordings.
Speaker labels are inserted at turn boundaries.
Download per-file transcripts or a combined JSON.
Yes — pause- and channel-based turn detection labels speakers as Speaker 1, Speaker 2, etc.
Yes. Drop several files and they're processed sequentially so the browser stays responsive.
No. Everything runs in your browser.
Transcribe MP3, WAV, M4A, OGG or FLAC into text with Whisper.
Speak into your mic and watch words appear — fully on-device.
Generate SRT and WebVTT captions for any video file.
Long-form transcript with timestamps for episodes and interviews.
Record a meeting and transcribe with headings and bullet notes.
Dictate a quick note and save it as a .md file.
Whisper translate mode — convert any language into English.
Identify the spoken language of any short audio clip.
Zro7