bedriyan/speaky
Voice-to-text for macOS, powered by on-device AI. Press a hotkey, speak, and the transcription is pasted at your cursor.
Built on Swift 6 with a modular architecture, Speaky supports multiple transcription engines—CoreML-based Parakeet V3 for Apple Silicon, whisper.cpp for cross-platform local inference, and optional Groq API integration for cloud transcription. The app includes intelligent post-processing with automatic filler-word removal and capitalization correction, plus advanced UI features like dynamic notch overlays with real-time waveforms and an animated mascot character that reflects recording/transcribing state.
Stars
5
Forks
2
Language
Swift
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/bedriyan/speaky"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
amicalhq/amical
🎙️ AI Dictation App - Open Source and Local-first ⚡ Type 3x faster, no keyboard needed. 🆓...
kstonekuan/tambourine-voice
Your personal voice interface for any app. Speak naturally and your words appear wherever your...
Notely-Voice/NotelyVoice
A 100% private AI voice transcription app that converts speech to text in 100+ languages. Built...
Saik0s/Whisperboard
The open-source iOS app that's making quality voice transcription more accessible on mobile devices.
sveinbjornt/hear
Command line interface for the built-in speech recognition and transcription capabilities in macOS.