TokenRex
Models & PricingFeaturesIntegrationsDocsFAQ
Get API
Home/Features/Music generation
Feature

Music generation

Lyria 3 creates music with vocals or instrumentals — clips or full tracks.

Google's Lyria 3 models generate original music from a text description or an image. Lyria 3 Clip makes 30-second clips for intros and stingers; Lyria 3 Pro produces full tracks up to about three minutes with vocals or instrumentals. Every track is billed per generation from the same wallet.

Clip
~30 seconds
Pro
Up to 3:04
Style
Vocals or instrumental

What you get

  • Text or image prompts
  • 30-second clips or full three-minute tracks
  • Vocals and instrumentals
  • Ideal for intros, ads, games and social content
  • Same key and wallet as every other model

Common use cases

Podcast introsAd soundtracksGame musicSocial videosApp sounds

How it works

  1. 1
    Create your account and key
    Sign up, top up your wallet and generate an API key from the dashboard.
  2. 2
    Describe the music
    POST a text description (or an image) to the music endpoint with your chosen Lyria model.
  3. 3
    Download the track
    Receive the finished MP3 and use it in your product.
  4. 4
    Pay per track
    Each generation is charged at the model's live market price.

Code examples

1
2
3
4
5
6
7
curl https://tokenrex.ai/api/public/music \
  -H "Authorization: Bearer sk-tb-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "lyria-3-pro",
    "prompt": "Upbeat acoustic intro for a tech podcast, 30 seconds"
  }'

Frequently asked questions

Clip or Pro — which do I need?

Lyria 3 Clip makes ~30-second clips; Lyria 3 Pro makes full tracks up to about three minutes. Prices for both are listed below.

Can the music have vocals?

Yes. Lyria 3 supports vocals and instrumentals — describe what you want in the prompt.

Can I prompt with an image?

Yes. Lyria 3 accepts an image as the creative prompt as well as text.

Related features

Video generation

Create short video clips from text or images with Gemini Omni and Veo 3.1.

Images, speech & embeddings

GPT Image 2.5, Gemini image models, text-to-speech, transcription and embeddings.

Playground

Chat, talk and create with any model in your browser before writing code.

Get API key Models & PricingCost calculatorAPI documentation
All featuresNext: Images, speech & embeddings

Live pricing & comparison

Live per-track market prices for every music model.

Music

ModelInputOutput / unit
lyria-3-clip-preview

30-second music clips, loops and previews — vocals or instrumentals, from text or an image

—$0.04 / per clipDetails
lyria-3-pro-preview

Full-length songs up to ~3 minutes with verses, choruses and timed lyrics

—$0.08 / per songDetails

Live market prices in your display currency. Full details, cache rates and variants on each model page and the Models & Pricing page.