speech-swift
On-device speech recognition, synthesis, and voice AI for Apple Silicon
All Skills in This Repository (3)
Pure Emerald Level Indicators
soniqobenchmark
Benchmark on-device ASR, TTS, VAD, and diarization latency and efficiency.
soniqotest
Run Swift unit or end-to-end test suites against a local codebase.
soniqoreview-pr
Reviews pull requests for architecture fit, security risk, test coverage, and merge readiness.
Frequently Asked Questions
FAQPage SchemaHow to install speech-swift?▼
Run `npx skills add soniqo/speech-swift --all -g -y` in your terminal to install all skills in this suite globally.
What does speech-swift do?▼
It runs speech recognition, text-to-speech, voice cloning, translation, and speaker diarization entirely on-device on Apple Silicon Macs and iPhones, with no cloud or API keys required.
How to run tests safely in speech-swift?▼
Use the /test skill: `/test unit` for quick checks or `/test e2e` for full model-based tests, which run in isolated processes to avoid exhausting system memory.
Can AI agents review pull requests in this repo?▼
Yes. The /review-pr skill checks architecture fit, security, regression risk, and test coverage, then gives a clear merge recommendation.
Does speech-swift work offline?▼
Yes. All models download once from HuggingFace and then run fully offline on your device, so no audio data ever leaves your machine.
Related Repositories in Software Engineering
View All in Software Engineering→
openclawopenclaw
Run a personal AI assistant across your devices and chat apps
obrasuperpowers
Gives coding agents a disciplined workflow from idea to merged code
facebookreact
AI agent skills for building, testing, and porting React core