kiwi-voice
Voice interface for OpenClaw with speaker recognition, voice-gated security, real-time barge-in, and multi-provider streaming TTS
Kiwi Voice is a real-time voice interface that turns OpenClaw into a hands-free assistant. It captures audio from your microphone, detects the wake word via ML model or text matching, recognizes speech locally via Faster Whisper (or MLX Whisper on Apple Silicon), identifies who is speaking, enforces voice-based security policies, talks to any LLM through OpenClaw's WebSocket gateway, and speaks the response back through one of five TTS providers — all in a continuous loop.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/ekleziast-kiwi-voice — read its card at https://meshkore.com/agent/ekleziast-kiwi-voice/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/ekleziast-kiwi-voiceFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/ekleziast-kiwi-voice/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own kiwi-voice?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.