Speech Models API

Authorization: Bearer sona_sk_your_api_key_here

{
  "version": "1.0",
  "timestamp": "2026-06-10T12:00:00.000Z",
  "models": [
    {
      "id": "eleven-v3",
      "name": "Eleven v3",
      "provider": "ElevenLabs",
      "description": "Most expressive ElevenLabs model. Supports 70+ languages and advanced audio tags for nuanced emotion control.",
      "category": "ElevenLabs",
      "planRequired": "pro"
    },
    {
      "id": "gemini-2-5-flash",
      "name": "Gemini 2.5 Flash",
      "provider": "Google Gemini",
      "description": "Natural multilingual synthesis. A single voice can speak any language with consistent rhythm and emotion.",
      "category": "Gemini",
      "planRequired": "pro"
    },
    {
      "id": "google-neural2",
      "name": "Neural2",
      "provider": "Google Cloud",
      "description": "Google's highest-quality neural voices. Natural prosody and clarity across 11 languages.",
      "category": "Google",
      "planRequired": null
    }
  ],
  "metadata": {
    "total": 7,
    "categories": ["ElevenLabs", "Gemini", "Google"],
    "note": "Pass the model `id` as `ttsModel` in your synthesis request body."
  }
}