local VAD collects a spoken utterance,
Athena Whisper transcribes it,
OpenClaw's normal agent-consult path answers with its configured model and tools,
Athena Qwen3-TTS returns PCM audio to the Talk client.

Long replies are synthesized incrementally. The first short phrase starts playing as soon as it is ready while the next phrase is generated in parallel.

The provider intentionally uses half-duplex audio: microphone input is paused while a response is being transcribed, generated, synthesized, or played. This prevents speaker feedback from aborting TTS. Spoken interruption (barge-in) is therefore disabled; wait until playback finishes before speaking again.

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:

{
  "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.