Audio Narration API - Listen to the Urantia Book - Urantia.dev

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://cdn.urantia.dev/audio/eng/paragraphs/nova/tts-1-hd-nova-0:0.0.1.mp3",
        "bitrate": 160,
        "duration": 43.3,
        "fileSize": 866400
      }
    },
    "gpt-4o-mini-tts": {
      "cedar": {
        "format": "mp3",
        "url": "https://cdn.urantia.dev/audio/eng/paragraphs/cedar/gpt-4o-mini-tts-cedar-0:0.0.1.mp3",
        "bitrate": 192,
        "duration": 41.7,
        "fileSize": 1002518
      }
    }
  }
}

bitrate is in kbps, duration in seconds, and fileSize in bytes.

Available models and voices

Coverage varies per paragraph. Only the tts-1-hd / nova combination covers every paragraph. Read the audio object rather than building URLs by hand — a voice that is absent for a paragraph is absent from the object.

Model	Voices	Coverage
`tts-1-hd`	`nova`	Full — all 14,500+ paragraphs
`gpt-4o-mini-tts`	`cedar`	Partial — roughly 3,400 paragraphs
`tts-1-hd`	`onyx`	Partial — a few hundred paragraphs
`tts-1-hd`	`echo`, `alloy`, `fable`, `shimmer`	Samples only
`tts-1`	`alloy`	Samples only

Accessing audio

Audio URLs are included in responses from all paragraph-returning endpoints: /search, /paragraphs/*, /papers/:id, and the dedicated /audio/:ref endpoint.

# Get just the audio info for a paragraph
curl https://api.urantia.dev/audio/119:1.5

All audio files are served from cdn.urantia.dev via Cloudflare CDN. See CDN & Static Assets for the URL patterns and for paper-level audio.