API docs / Audio models
Lyria 3.5 API
Generate a song or instrumental from one prompt with style, timed sections and optional lyrics or mood image.
- Model id
google/lyria-3.5- Provider
- Output
- Audio
- Price
- From 35 credits per run, the same as on voor.ai. Options such as length or resolution can change it.
Request
POST https://voor.ai/v1/generations with "model": "google/lyria-3.5". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.
curl https://voor.ai/v1/generations \
-H "Authorization: Bearer $VOOR_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "google/lyria-3.5",
"input": {
"prompt": "A red fox standing in fresh snow at golden hour, soft light"
},
"callback_url": "https://example.com/webhooks/voor"
}'
# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
-H "Authorization: Bearer $VOOR_API_KEY"Input parameters
| Name | Type | Details |
|---|---|---|
promptrequired | string | Describe genre, mood, tempo, instruments and vocal style. Plan the structure with timestamped sections such as [0:00-0:20] Intro, and put your own lyrics under a Lyrics: heading with [Verse] and [Chorus] tags. Write 'instrumental, no vocals' for a track without singing. Vocals can be English, Spanish, German, French, Portuguese, Hindi, Japanese or Korean. Up to 5000 characters |
reference_images | array of URLs | Optional image the music should match in mood and theme. The prompt still decides genre, length and lyrics. Up to 1 files · Accepts image/* |