Skip to main content
Every paragraph includes an audio field — a nested object keyed by TTS model and voice, or null if no audio exists.

​
Response shape

{
  "audio": {
    "tts-1-hd": {
      "nova": {
        "format": "mp3",
        "url": "https://audio.urantia.dev/tts-1-hd-nova-3:119.1.5.mp3"
      },
      "echo": {
        "format": "mp3",
        "url": "https://audio.urantia.dev/tts-1-hd-echo-3:119.1.5.mp3"
      }
    },
    "tts-1": {
      "alloy": {
        "format": "mp3",
        "url": "https://audio.urantia.dev/tts-1-alloy-3:119.1.5.mp3"
      }
    }
  }
}

​
Available models and voices

Coverage varies per paragraph. The tts-1-hd / nova combination has full coverage across all 14,500+ paragraphs.
ModelVoices
tts-1-hdnova, echo, onyx, alloy, fable, shimmer
tts-1alloy

​
Accessing audio

Audio URLs are included in responses from all paragraph-returning endpoints: /search, /paragraphs/*, /papers/:id, and the dedicated /audio/:paragraphId endpoint. 
# Get just the audio info for a paragraph
curl https://api.urantia.dev/audio/119:1.5
All audio files are served from audio.urantia.dev via Cloudflare CDN.