Audio Drop turns audio files into full transcripts with automatic speaker detection — drop in a meeting recording or interview and get back who said what. Processing happens entirely on your Mac.
Transcribing a File
- Go to the Audio Drop tab in the sidebar.
- Drag an audio file in, or click to pick one. Common formats are supported (MP3, WAV, AIFF, M4A, and more).
- Watch the progress bar — you can Cancel at any point. Long, multi-hour files are processed in streaming chunks.
Speakers
- Speakers are detected automatically and each gets its own color.
- Click a speaker label to rename "Speaker 1" to a real name — the whole transcript and all exports update.
- If voices can't be separated, the transcript gracefully falls back to a single speaker.
Timestamps
Choose one of three timestamp modes: off, once per speaker turn (default), or every sentence.
Exporting
Export the transcript in five formats, each with Copy and Save options:
- Plain text
- Markdown
- SRT subtitles
- JSON
- CSV
