local-voice
par trondw
DevOps & CloudRésumé
Local text-to-speech (TTS) and speech-to-text (STT) using FluidAudio on Apple Silicon.
Description
Ce que fait ce skill
Runs text-to-speech and speech-to-text entirely on Apple Silicon using FluidAudio's CoreML models via the Apple Neural Engine. TTS uses the Kokoro model with 54 voices at ~0.6-0.8s latency; STT uses Parakeet TDT v3 with ~0.2-0.3s latency across 25 languages. No network connection or API key required.
Achieves sub-second voice synthesis and transcription on-device, replacing cloud TTS/STT services without API costs, rate limits, or sending audio data off-device.
Quand l'utiliser
- Reading long articles aloud while multitasking
- Transcribing recorded meetings without uploading audio to the cloud
- Adding offline voice output to a local AI assistant
- Converting written notes to audio files for listening on the go
- Building voice interfaces for local automation scripts
Exemple de workflow
User asks: Read this paragraph aloud
- 1
Receives text input from the user
- 2
POSTs text to the local TTS endpoint at http://127.0.0.1:18790/synthesize
- 3
StellaVoice daemon processes the request using the Kokoro model on the Apple Neural Engine
- 4
Returns a WAV file in approximately 0.6-0.8 seconds
- 5
Plays the audio output to the user
The paragraph is spoken aloud in the selected Kokoro voice with natural pacing
Prérequis
- Apple Silicon Mac (M1 or newer) running macOS 14+
- espeak-ng (install via Homebrew: brew install espeak-ng)
Installation
clawhub install trondw/local-voiceExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.