Seedance 2.0 is here - create consistent, multimodal AI videos faster with images, videos, and audio in one prompt.

Try Now
Skip to main content
Available now on ModelsLab · Voice & Audio

Lyria 3Lyria 3 Music Generation

Sample output

Generate Tracks Instantly

Vocal Control

Custom Voice Styles

Specify gender, range, timbre for realistic vocals in 8 languages.

Text-to-Music

Prompt to Track

Turn text prompts into 30-second songs with lyrics and structure.

API Access

Lyria 3 API

Integrate Lyria 3 model via API for scalable music generation.

Examples

See what Lyria 3 can create

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

Epic Orchestral

Create an epic orchestral track with soaring strings, deep brass, and commanding baritone vocals singing in English about ancient mountains at dawn, 120 BPM, building to crescendo.

Chill Jazz

Generate chill jazz instrumental with smooth saxophone, upright bass, breathy female soprano vocals in Portuguese, laid-back groove, 80 BPM, fading piano outro.

Urban Beats

Produce urban hip-hop beat with heavy bass, fast-paced rap in Spanish by gravelly male voice, synth accents, 95 BPM, dynamic verse-chorus structure.

Dreamy Ambient

Soulful ambient track with ethereal synths, soft Hindi lyrics by high soprano, reverb-heavy timbre, slow tempo 60 BPM, evolving textures.

For Developers

A few lines of code.
Music from text. One 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 second, no minimums
  • Python and JavaScript SDKs, plus REST API
import requests
response = requests.post(
"https://modelslab.com/api/v7/voice/music-gen",
json={
"key": "YOUR_API_KEY",
"prompt": "An upbeat Afrobeat song with energetic percussion, groovy bassline, and rhythmic guitar riffs. The vocals are clear and uplifting, with lyrics about dancing together, freedom, and feeling alive under the city lights",
"init_image": "https://assets.modelslab.ai/generations/9c2b6fa0-0a2a-49f1-b6f4-367203e05afc.webp"
}
)
print(response.json())

FAQ

Common questions about Lyria 3

Read the docs

Lyria 3 API enables text-to-music generation with vocals and structure. Access via endpoints for 30-second tracks. Supports developer integration like Gemini API.

Lyria 3 offers granular voice customization via prompts for gender, range, timbre. No direct audio upload cloning. Use as Lyria 3 voice cloning alternative.

Supports vocals in 8 languages: English, German, Spanish, French, Hindi, Japanese, Korean, Portuguese. Specify in prompts for multi-language singing.

Lyria 3 generates 30-second clips ideal for prototyping. Lyria 3 Pro extends to 3 minutes with structure. Both via lyria 3 api.

Yes, with improved realism, expressiveness, and controls for timbre, patterns. Supports multi-vocal layers. Better than prior models.

Lyria 3 API provides high-fidelity text-to-music on ModelsLab. Matches Google features like prompt control. Scalable for production.

Ready to create?

Start generating with Lyria 3 on ModelsLab.