{
  "description": "Convert text to speech audio. Returns a MEDIA: path that the platform delivers as native audio. Compatible providers render as a voice bubble on Telegram; otherwise audio is sent as a regular attachment. In CLI mode, saves to ~/voice-memos/. Voice and provider are user-configured (built-in providers like edge/openai or custom command providers under tts.providers.<name>), not model-selected.",
  "name": "text_to_speech",
  "parameters": {
    "properties": {
      "instructions": {
        "description": "Optional voice-design guidance: tone, emotion, pacing, accent, whispering, impressions (e.g. 'Speak in a cheerful, excited whisper'). Forwarded to the OpenAI backend (gpt-4o-mini-tts and OpenAI-compatible voice-design servers). Silently ignored by backends that don't support it.",
        "type": "string"
      },
      "output_path": {
        "description": "Optional custom file path to save the audio. Defaults to ~/.hermes/audio_cache/<timestamp>.mp3",
        "type": "string"
      },
      "speed": {
        "description": "Playback speed multiplier. 1.0 = normal, 0.5 = very slow (language learning), 2.0 = fast. Range: 0.25-4.0. Overrides the speed configured in config.yaml.",
        "type": "number"
      },
      "text": {
        "description": "The text to convert to speech. Provider-specific per-request character caps apply automatically (OpenAI 4096, xAI 15000, MiniMax 10000, ElevenLabs 5k-40k depending on model); longer input is split into ordered chunks without silent truncation.",
        "type": "string"
      }
    },
    "required": [
      "text"
    ],
    "type": "object"
  }
}