Add private realtime Talk for OpenClaw

This commit is contained in:
Mikei386
2026-09-03 22:52:15 +02:00
parent 42ec28c9f6
commit 0a68df22eb
10 changed files with 829 additions and 11 deletions
@@ -0,0 +1,39 @@
# Athena Local Talk for OpenClaw
This private OpenClaw provider connects browser/Desktop Talk to the existing
Athena speech stack:
1. local VAD collects a spoken utterance,
2. Athena Whisper transcribes it,
3. OpenClaw's normal agent-consult path answers with its configured model and
tools,
4. Athena XTTS/Piper returns PCM audio to the Talk client.
No public speech provider is used. The provider reuses the already configured
`models.providers.athena` base URL and API key; no second key copy is required.
Recommended `talk.realtime` configuration:
```json
{
"provider": "athena-talk",
"model": "athena-local",
"speakerVoice": "alloy",
"language": "de",
"mode": "realtime",
"transport": "gateway-relay",
"brain": "agent-consult",
"providers": {
"athena-talk": {
"vadThreshold": 0.018,
"silenceDurationMs": 750,
"prefixPaddingMs": 300,
"maxSpeechSeconds": 45
}
}
}
```
Install from the OpenClaw container with `openclaw plugins install <path>` and
restart the gateway once. The plugin is stored in OpenClaw's persistent data
directory, so normal image updates do not remove it.