ekleziast/kiwi-voice

Voice interface for OpenClaw with speaker recognition, voice-gated security, real-time barge-in, and multi-provider streaming TTS

32
/ 100
Emerging

Combines ML-based wake word detection via ONNX models with local STT (Faster Whisper or MLX Whisper on Apple Silicon) and speaker identification through voiceprint embeddings, enabling voice-gated command execution with hierarchical access control. Streams responses in real-time to multiple TTS providers (ElevenLabs, Kokoro, Piper, Qwen3) with sentence-aware chunking and interrupt capability, communicating with OpenClaw via native WebSocket gateway protocol. Includes web dashboard with browser-based microphone support, multi-language localization, and automatic speaker enrollment for privacy-first self-hosted voice interactions.

No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 9 / 25
Community 9 / 25

How are scores calculated?

Stars

7

Forks

1

Language

Python

License

MIT

Last pushed

Mar 04, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ekleziast/kiwi-voice"

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