Straight answers.

Press your hotkey, speak naturally, and oto places the finished text at your cursor. It works in any app that accepts text: Mail, Slack, Notes, Docs, Cursor, ChatGPT, and more.

You can tap to toggle, hold for push-to-talk, or use single-key hotkeys when Input Monitoring is enabled.

oto requires macOS 14 or later. It is optimized for Apple Silicon Macs and also supports Intel Macs.

Yes. You can try oto through TestFlight before buying. It is the full app, with no auto-charge.

oto is meant to be quiet software: present when you need it, out of the way when you do not. The name also means "sound" in Japanese.

Transcription runs locally on your Mac. oto does not require an account, does not include app telemetry, and does not upload audio for transcription.

No. Whisper, Parakeet, and Apple SpeechAnalyzer run on your hardware. If you enable optional cloud AI cleanup, only transcript text is sent to the provider you configured. Audio is not sent for that feature.

Microphone is required for live dictation. Accessibility is used for global hotkeys and placing text where your cursor already is. Input Monitoring is used for single-key hotkeys. Files are used only when you choose an audio or video file to transcribe.

The app does not include product analytics SDKs. App Store payments are handled by Apple. If you email support, oto receives the email address and message you send so we can reply.

oto supports 100+ languages with automatic detection through Whisper models. You can speak in supported languages and mix languages in a single recording.

Yes. Whisper models can translate supported speech to English. Parakeet v3 and Apple SpeechAnalyzer output text in the language you speak.

oto supports common audio and video formats including WAV, MP3, M4A, AIFF, AAC, FLAC, CAF, MP4, and MOV.

Whisper supports 100+ languages and can translate to English. Smaller models are faster; larger models are more accurate.

Parakeet v3 is a fast local engine for supported languages. Apple SpeechAnalyzer is Apple's on-device speech engine on supported macOS versions.

Yes. Dictation and file transcription run offline after the app and model are available on your Mac. Optional cloud AI cleanup requires internet only if you turn it on.

Yes. Install the oto command from Settings → Advanced. From the terminal you can transcribe files with oto transcribe < file.m4a, start and stop recordings, and browse your history. Results land in the app's history too, so the terminal and the app share one record.

Yes. oto includes an MCP server. Settings → Advanced gives you a ready-to-paste config for Claude Desktop, Claude Code, Cursor, or any MCP client. Connected assistants transcribe audio through oto fully on-device, so there is no cloud transcription service in the loop and audio never leaves your Mac.

Yes. Long-form meeting recording captures your mic and the meeting audio as two echo-cancelled streams and gives you a two-sided transcript once the call ends, your side and the meeting side kept apart. It does not tell individual speakers apart within the meeting side. You can also import Teams recordings, and everything runs on your Mac.

oto runs transcription on your hardware instead of charging for a cloud transcription service by default. The product is intentionally sold as one purchase, not a subscription.

Yes. One Mac App Store purchase unlocks the full app. There is no subscription and no separate Pro tier.

Refunds are handled through Apple. You can also try oto through TestFlight first if you want to test the full app before purchasing.

Yes. One purchase can cover up to five family members through Apple's Family Sharing.