WhisperS2T is an optimized speech-to-text pipeline for the Whisper model with support for multiple inference engines.
Open source
24 alternativesOpenQuack
OpenQuack provides local voice dictation on macOS, inserting Whisper transcripts at the cursor.
About OpenQuack
OpenQuack is a menu-bar app for macOS for voice dictation. Press a hotkey to start, speak, then press it again to stop, and the transcript is pasted at the cursor in the current app, with a clipboard fallback.
Transcription runs on the Mac by default via WhisperKit on Apple Silicon, with no account, signup, or telemetry. Nothing leaves the device by default; an optional self-configured OpenAI-compatible remote endpoint and an experimental on-device LLM polish feature are opt-in and off by default.
Key features
- Hotkey start-stop dictation with configurable key binding
- Pastes transcript at cursor with clipboard fallback
- On-device Whisper transcription via WhisperKit on Apple Silicon
- 99-language support with automatic detection by default
- Automatic capitalization, punctuation, and filler-word cleanup
- Optional on-device LLM polish with editable prompt
Best for: Mac users who want to dictate text into any app without sending audio to a cloud service by default.
Good for
- Recording and transcription run locally by default with no account or telemetry
- Continues to work offline because default loop makes no API call
- MIT-licensed open source with public development history
Watch out for
- Limited to macOS, with local Whisper via WhisperKit on Apple Silicon
- On-device LLM polish is experimental and turned off by default
- Use of a larger remote model requires configuring your own endpoint
OpenQuack at a glance
- Category
- AI & Machine Learning › AI Speech Transcription
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Platforms
- macOS
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
OpenQuack alternatives
Tools and sites you could use instead, ranked by how closely they match.
The whisper.cpp repository provides a C and C++ port of OpenAI’s Whisper model.
Open source
24 alternatives
AI Dictation turns mixed Russian, Ukrainian, or Belarusian speech into text while preserving English work terms.
Free trial
24 alternatives
Vocova transcribes audio and video into text in more than 100 languages and accepts imports from named services.
KubeAI serves machine learning models on Kubernetes, including speech to text, language, vision, and embedding models.
Open source
24 alternatives
Faster Whisper runs Whisper transcription through the CTranslate2 inference engine.
Open source
12 alternativesPopular in AI Speech Transcription
Well-known listings from the same topic.
Transgatetransgate.aiWavewave.coRev.airev.aiGood Tapegoodtape.ioTalkNotestalknotes.ioSpeech to Notespeechtonote.com
OpenQuack FAQ
Does OpenQuack send audio or text off my Mac?
No, by default recording and transcription are fully local. The exception is a remote transcription endpoint you configure yourself, which is off by default.
How do I dictate with OpenQuack?
Press the hotkey once to start and again to stop; the transcript then appears at the cursor. Auto-stop after silence can also end recording.
What languages can it transcribe?
It supports 99 languages with auto-detect on by default, including English, Chinese, Japanese, Korean, Spanish, French, German, Italian, and Portuguese in Settings.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.