The formats you already have
WAV, MP3, M4A, AIFF, AAC, FLAC, and CAF, plus MP4 and MOV video, where oto transcribes the audio track. Whatever your recorder produced, it probably just works.
Transcribe audio files on your Mac without uploading them anywhere. Drop a recording into oto, let it transcribe on-device, and export plain text, Markdown, or JSON: interviews, voice memos, lectures, meeting recordings.
No converting, no uploading, no per-minute pricing. Drop the file you have and get the text you need.
WAV, MP3, M4A, AIFF, AAC, FLAC, and CAF, plus MP4 and MOV video, where oto transcribes the audio track. Whatever your recorder produced, it probably just works.
Queue several files and let them run. A semester of lectures or a folder of interviews becomes a stack of transcripts while you do something else.
Plain text for the doc, Markdown for your notes app, JSON for your pipeline. Whisper can also translate speech to English while it transcribes.
Add one recording or queue a batch, audio or video, straight from Finder.
Local engines like Whisper and Parakeet v3 transcribe on-device. Nothing is uploaded.
Save as TXT, Markdown, or JSON, and find every transcript again in searchable history.
Honest scope: oto is a dictation-first app that also transcribes files well. If your entire job is multi-hour batch transcription every day, a dedicated transcription tool may fit better. For everyone else, $8 covers it.
No. File transcription runs on your Mac's own hardware by default. The recording, and the transcript, stay on your machine.
Yes: 100+ languages with Whisper, with automatic language detection, and optional translation of speech to English while transcribing.
Transcribe your files on your own Mac, with no uploads and no per-minute fees. $8 once.