Install
openclaw skills install lessac-offline-voice-systemComplete offline voice system with high-quality Lessac TTS and faster-whisper speech recognition. Provides natural voice conversations without internet. Use...
openclaw skills install lessac-offline-voice-systemThis skill exists to restore a known-good OpenClaw native voice messaging setup.
faster-whisper transcription helper in ~/.openclaw/ttsfaster-whisper, edge-tts, and soundfileKeep the live routing in openclaw.json:
"messages": {
"ackReactionScope": "group-mentions",
"tts": {
"auto": "inbound",
"provider": "microsoft",
"providers": {
"microsoft": {
"voice": "en-IE-ConnorNeural",
"lang": "en-IE"
}
}
}
}
And explicitly enable the bundled Microsoft plugin:
"plugins": {
"entries": {
"microsoft": {
"enabled": true
}
}
}
edge is a legacy alias. Current OpenClaw normalizes that path to microsoft.
After applying the config, do a real manual gateway restart.
A hot reload / SIGUSR1 is not enough if the Microsoft speech provider is stale or unregistered.
transcribe-audiovoice_handler.pytts_edge_wrapper.pyvoice_integration.shcd /root/.openclaw/workspace/skills/lessac_offline_voice_system
./scripts/install.sh
microsoft: no provider registeredopenai: not configured