dokterbob/macos-speech-server

Local, fast and efficient Speech to Text (STT) and Text to Speech (TTS) on MacOS with OpenAI-compatible API.

39
/ 100
Emerging

Leverages FluidAudio's on-device CoreML models (Parakeet for STT, PocketTTS/Kokoro for TTS) via Apple's Neural Engine without cloud dependencies. Dual-protocol architecture supports OpenAI-compatible HTTP endpoints alongside Wyoming protocol for native Home Assistant voice pipelines. Models load once at startup and serve network-wide, enabling a single Apple Silicon Mac to handle transcription and synthesis for multiple devices.

No Package No Dependents
Maintenance 13 / 25
Adoption 5 / 25
Maturity 9 / 25
Community 12 / 25

How are scores calculated?

Stars

11

Forks

2

Language

Swift

License

AGPL-3.0

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/dokterbob/macos-speech-server"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.