Voice dictation for Apple Silicon Macs. Runs on your Mac, works offline, free and open source.
ProductivityTypeScript · HTMLGitHub @ali050786OnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
GitHub star growth between the latest completed 8-hour observations
DeepSeek Harness Remote can securely connect a phone or another computer to the computer where you run DeepSeek Harness, so you can continue your work anytime and anywhere, check progress anytime, and continue working.
AI translation
Open-source, local-first task manager that works offline, syncs every device, runs on a Raspberry Pi, and requires no subscription.
AI translation
Open-source, self-hosted webmail built on JMAP. Email, calendar, contacts, and files in one interface for Stalwart Mail Server.
Open Source Office suite for users used to MS Office - multi-platform, tuned for performance
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
Open-source voice dictation for macOS — local Whisper STT, optional LLM cleanup, native text injection into any app
Taken from the repository README
Loading the full README.
Read the full README ↗Voice dictation for macOS that runs on your Mac. Hold a key, speak, and the text appears in whatever field you're typing in, cleaned up by a local AI model. No word limits, and nothing leaves your Mac unless you choose the optional cloud cleanup with your own OpenRouter key.
Apple Silicon only.
Utter-<version>-arm64.dmg from Releases, open it and drag Utter into Applications.Nothing else to install: the speech engines (Phonon and WhisperKit) and the cleanup engine (mlx-lm) ship inside the app. The first run downloads the models, with progress shown in Settings: about 160 MB for speech (646 MB if you dictate in a language Phonon doesn't cover, such as Hindi), and 1.7 GB (English) or 4.3 GB (other languages) for cleanup.
After rebuilding and reinstalling, macOS may ask for Accessibility again.
Building needs Homebrew's whisperkit-cli (copied into the app) and uv (fetches the bundled Python, with mlx-lm and Phonon's fermion-research, minus the PyTorch it only needs on other platforms):
brew install whisperkit-cli
npm install && npm run make
npm run make runs scripts/build-engines.sh and writes out/make/dmg/arm64/Utter-<version>-arm64.dmg.
Settings, history and your dictionary are in the app window: click the menu-bar icon → Open Utter. Data is kept in ~/.dictateai (readable only by you).
Settings → Speech model → Automatic picks by your dictation language:
| Language | Model | Download |
|---|---|---|
| English | Phonon-2 | 158 MB |
| Auto-detect, and 24 other European languages (French, German, Spanish, Russian, Ukrainian…) | Phonon-2.5 | 156 MB |
| Everything else (Hindi, Arabic, Japanese, Chinese…) | Whisper Large v3 Turbo | 646 MB |
Phonon transcribes 7.6 seconds of speech in about 0.15 s on an M-series Mac, and the words in your dictionary are passed to it as hotwords, so it favours your spellings of names and terms. Auto-detect only hears Phonon-2.5's languages; to dictate in Hindi, choose Hindi. Settings can also run Whisper (Small or Large v3 Turbo) for every language.
Phonon-2 and Phonon-2.5 are by Fermion Research, derived from NVIDIA's Parakeet TDT 0.6B v3, and released under CC-BY-4.0. They run through the fermion-research package (Apache 2.0).
npm run build:engines && npm start
Set UTTER_DEBUG=1 to log dictated text; by default logs show only its length.
npm test runs the unit tests (Node 23.6 or later, which runs TypeScript directly). The start and stop sounds are generated by npm run build:sounds.
The landing page, utter.blinkwiser.com, is site/: one static page, plus two small Vercel functions that look up the newest release on GitHub. /download sends visitors to its .dmg, and the page's buttons show its version and size. To host it on Vercel, import the repository and set Root Directory to site (framework preset: Other, no build command). Elsewhere, the page still works and its buttons open the Releases page. An optional GITHUB_TOKEN environment variable raises GitHub's limit of 60 lookups an hour, which the 10-minute cache rarely reaches.
Utter was called DictateAI until October 2026. Its data folder (~/.dictateai) and bundle ID keep that name, so settings, history, models and macOS permissions carry over.
How this version was built, and why: docs/sessions/2026-10-18-session.md.