Update to EmpirioLabs AI

{
  "description": "Turn text into natural speech. Use for voiceovers, narration, read-alouds, audio versions of an article and lines spoken in a chosen voice or language.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 236
    }
  ],
  "name": "ai-voice-generator",
  "skill_md_contents": "---\nname: ai-voice-generator\ndescription: Turn text into natural speech. Use for voiceovers, narration, read-alouds, audio versions of an article and lines spoken in a chosen voice or language.\n---\n# Voiceover\n\n1. Fix the exact text to speak. Ask only when it is missing.\n2. Choose a speech model: call `list_models` with `endpoint` set to `/v1/audio/speech`, unless the user names a model.\n3. Choose a voice: call `list_voices` with that `model`. Filter by `language`, written as its English name such as `Spanish`, or by `gender`, when the user asks for one. Pick a voice that fits the request.\n4. Call `text_to_speech` with the `model`, the text as `input` and the `voice`.\n5. Reply with the audio link, the voice and the model.\n\nFor a different voice, list the voices again and offer three by name.\n"
}