Audio model API
Lyria 3.5 API
Lyria 3.5 is Google DeepMind’s latest music-generation model, designed to create full-length, structured songs from text prompts and image-based musical inspiration. It can generate music across different genres and moods while giving creators control over elements such as tempo, instrumentation, vocals, lyrics, and song structure. Unlike short music-clip generators, Lyria 3.5 is designed for songs lasting up to a few minutes, with generated MP3 audio at 44.1 kHz stereo and optional lyrics. It also supports multiple languages, including English, German, Spanish, French, Hindi, Japanese, Kor
- Model id
lyria-35- Takes
- Text (required)
- Makes
- Audio
- Endpoint
POST /api/v1/run- Made by
- Mode
- Synchronous
Call Lyria 3.5
https://payload.rentprompts.com/api/v1. Replace the placeholder with your key.Model lyria-35
POST /api/v1/runasync · poll /v1/jobs/:id
curl https://payload.rentprompts.com/api/v1/run \
-H "Authorization: Bearer rp_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "lyria-35",
"prompt": "A calm lo-fi beat with soft piano"
}'
# Async models answer HTTP 202 with a job. Poll it until status is
# "succeeded" (output.url / output.urls) or "failed" (error):
curl https://payload.rentprompts.com/api/v1/jobs/JOB_ID \
-H "Authorization: Bearer rp_live_YOUR_KEY"Replace rp_live_YOUR_KEY with your key, ideally via the RENTPROMPTS_API_KEY environment variable. Keys are shown only once, so they are never filled in here. Get your API key →
What a typical call costs
- 1 request11 Joules
- 10 requests110 Joules
Send requests to POST /api/v1/run. Lyria 3.5 answers synchronously: the result comes back in the response to the same request.
Settings
This model has no extra settings. Send the standard fields shown in the example.