Lyria 3 Pro Preview via the Tokenator API
What the model is for
Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz stereo audio from text prompts or from images. These models deliver structural coherence, including vocals, timed lyrics, and full instrumental arrangements. Lyria 3 Pro can generate full-length songs with verses, choruses, bridges.
Specification
| Full name | Lyria 3 Pro Preview |
| API ID | lyria-3-pro-preview |
| Model vendor | Gemini |
| Type | Music generation |
| Context window | 1.05M tokens |
| Audio formats | mp3, wav |
| Default format | mp3 |
| Base price | 800000 tokens per successful generation |
| Tokenator usage multiplier | 1× |
| Badge | NEW |
| Input modalities | text, image |
| Supported API formats | /v1/audio/generations |
| Upstream providers | 1 |
| Current status | available |
| Data updated | 2026-11-05 |
Upstream providers
| Provider | Multiplier |
|---|---|
| Unified LLM API | 1× |
A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.
Example request
curl https://api.tokenator.top/v1/audio/generations \ -H "Authorization: Bearer sk-your-tokenator-key" \ -H "Content-Type: application/json" \ --output music.mp3 \ -d '{ "model": "lyria-3-pro-preview", "prompt": "A gentle piano melody with a warm atmosphere", "response_format": "mp3" }'
See also
FAQ about Lyria 3 Pro Preview
What is the API ID of Lyria 3 Pro Preview?
lyria-3-pro-preview — put this into the model field of your request.
How do I call this model?
Send POST /v1/audio/generations with the model's API ID. Request examples and parameters are in the audio documentation.
Why is the model absent from /v1/models?
Audio models have a separate catalog at GET /v1/audio/models. Use ?task=tts for synthesis or ?task=stt for transcription; use ?task=music for music. Chat endpoints refuse audio models.
Which API key should I use?
Use your regular Tokenator key with access to this model. Send it in the Authorization: Bearer sk-your-tokenator-key header.
How do I describe the track?
Describe the genre, mood and instruments in prompt. Use lyrics for lyrics, instrumental=true for music without vocals and duration for a target length in seconds; the result depends on the model.
How do I get the finished music?
The request returns a complete binary audio file. Use --output music.mp3 with curl. Select response_format from audio_options.formats. Each request generates one track.