Lyria 2 is Google DeepMind's music generation model, capable of producing full instrumental compositions and musical arrangements from text prompts. It supports a wide range of genres, tempos, and instrumentation styles, allowing users to describe the mood, genre, or context of the music they need and receive original audio output.
Built for creative applications, Lyria 2 is positioned as a tool for content creators, game developers, and media producers who need custom, royalty-free music. Google has integrated it into products like YouTube Dream Track and made it accessible via API for platform developers.
Key Features
Text-to-music generation across diverse genres and styles
Control over tempo, mood, instrumentation, and arrangement density
Produces full stereo instrumental tracks suitable for media use
Supports short motifs through to longer compositional pieces
Integrated into Google's creative tooling ecosystem and available via API
Ideal Use Cases
Background music for YouTube videos and social media content
Custom soundtracks for indie games and interactive experiences
Podcast and audiobook intro or ambient audio generation
Rapid music prototyping for film and advertising production
Example Prompts for Lyria 2
Technical Specifications
| Provider | |
| Category | Audio |
| Modality | Text -> Audio |
API Usage
1 curl -X POST https://api.vincony.com/v1/chat/completions \ 2 -H "Authorization: Bearer YOUR_API_KEY" \ 3 -H "Content-Type: application/json" \ 4 -d '{ 5 "model": "google/lyria-2", 6 "messages": [ 7 { "role": "user", "content": "Hello, Lyria 2!" } 8 ] 9 }'
Replace YOUR_API_KEY with your Vincony API key. OpenAI-compatible endpoint — works with any OpenAI SDK.
Frequently Asked Questions
Try Lyria 2 now
Start using Lyria 2 instantly — 100 free credits, no credit card required. Access 800+ AI models through one platform.
More from Google
Use ← → to navigate between models · Esc to go back