Audio LLMs

import base64, requests

# 1. Capture audio with the hot mic
self.capability_worker.start_audio_recording()
await self.worker.session_tasks.sleep(10)  # or wait for a stop command
self.capability_worker.stop_audio_recording()
audio_bytes = self.capability_worker.get_audio_recording()

# 2. Send to a multimodal audio model via OpenRouter
response = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_OPENROUTER_KEY"},
    json={
        "model": "google/gemini-2.5-flash-preview",
        "messages": [{
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe this sound. What's happening?"},
                {"type": "input_audio", "input_audio": {
                    "data": base64.b64encode(audio_bytes).decode(),
                    "format": "wav",
                }},
            ],
        }],
    },
    timeout=30,
)
analysis = response.json()["choices"][0]["message"]["content"]
await self.capability_worker.speak(analysis)