Happy Horse 1.0 is now on ModelsLab

Try Now
Skip to main content
Available now on ModelsLab · Language Model

Google: Lyria 3 Pro PreviewGenerate Full Songs Instantly

Try Google: Lyria 3 Pro PreviewAPI Documentation

Prompt. Structure. Produce.

Full-Length Tracks

Up to 3 Minutes

Create complete songs with Google: Lyria 3 Pro Preview, including intros, verses, choruses, bridges.

Precise Control

Tempo Lyrics Structure

Set tempo, align lyrics time-precisely, and define sections using Google: Lyria 3 Pro Preview API.

Multimodal Input

Text Image Prompts

Convert text or images to music with the Google: Lyria 3 Pro Preview model for mood and style.

Examples

See what Google: Lyria 3 Pro Preview can create

Copy any prompt below and try it yourself in the playground.

Epic Orchestral Intro

“Generate a 3-minute orchestral track: slow intro building to fast tempo, epic strings and brass, cinematic atmosphere inspired by a starry night sky image, no vocals.”

Upbeat Electronic Verse

“Create electronic dance track up to 3 minutes: intro with synth pads, verse at 128 BPM, chorus drop with bassline, bridge slowdown, futuristic cityscape mood from image.”

Acoustic Folk Song

“Produce acoustic folk song 2:30 long: gentle guitar intro, verse with soft vocals 'Wandering through ancient forests', chorus uplift, bridge instrumental, nature landscape influence.”

Jazz Piano Ballad

“Jazz piano ballad 3 minutes: moody intro, verse slow 70 BPM with improvised sax, chorus emotional peak, bridge resolution, rainy urban night image for atmosphere.”

For Developers

A few lines of code.
Music tracks. One API call.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per token, no minimums
  • Python and JavaScript SDKs, plus REST API
API Documentation 
import requests


response = requests.post(
    "https://modelslab.com/api/v7/llm/chat/completions",
    json={
  "key": "YOUR_API_KEY",
  "prompt": "",
  "model_id": ""
}
)
print(response.json())

FAQ

Common questions about Google: Lyria 3 Pro Preview

Read the docs

Google: Lyria 3 Pro Preview is an advanced AI music generation model for full songs up to 3 minutes. It supports structural prompts like intros and choruses. Access via Google: Lyria 3 Pro Preview API.

Send text or image prompts to generate tracks with tempo, lyrics, and sections. It outputs studio-quality audio up to 3 minutes. Ideal for developers via Gemini API integration.

Features structural awareness, multimodal inputs, and precise controls like time-aligned lyrics. Generates professional tracks unlike shorter clip models. Preview enables experimentation.

This preview offers full-length generation not matched by basic models. Use for premium output in apps like Vertex AI. Compare via Google: Lyria 3 Pro Preview LLM endpoints.

Yes, with improved realism and expressiveness. Prompt for lyrics timed to sections. Combine with instrumental elements for complete songs.

Available in Vertex AI, Google AI Studio, Gemini API. Start with prompts for music production. Documentation covers integration.

Ready to create?

Start generating with Google: Lyria 3 Pro Preview on ModelsLab.

Try Google: Lyria 3 Pro PreviewAPI Documentation