Lyria 3 Pro Preview
Lyria 3 Pro Preview is a music generation model developed by Google. It allows users to create high-quality, 48kHz audio output from text and image inputs. This model is currently available for free through the Gemini API.
Lyria 3 Pro Preview specs and pricing
- Provider: Google
- Released: March 30, 2026
- Context window: 1M tokens
- Max output: 66K tokens
- Input: text, images
- Output: text, audio
- Price: free
What Lyria 3 Pro Preview is good at
- Generating original musical compositions
- Creating audio assets from text descriptions
- Transforming visual concepts into musical tracks
To-dos to try with Lyria 3 Pro Preview
- Generate a three-minute upbeat jazz track based on this image of a rainy city street
- Compose a background melody for a video project using a text description of a forest atmosphere
- Create a high-fidelity audio file from a prompt describing a classical piano piece
FAQ
- What kind of content can Lyria 3 Pro Preview generate? The model generates high-quality, 48kHz audio output.
- What types of input does the model accept? You can provide both text and images as inputs to guide the music generation process.
- How much does Lyria 3 Pro Preview cost? Lyria 3 Pro Preview is available as a free model. In todo.is it doesn't use credits, though free models can be rate-limited by the provider.
- What is the context window of Lyria 3 Pro Preview? Lyria 3 Pro Preview can read up to 1M tokens at once and write up to 66K tokens in one reply.
- Can I use Lyria 3 Pro Preview without coding? Yes. In todo.is you pick Lyria 3 Pro Preview as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.