Report
Gemini app adds Lyria 3 music generation for 30-second tracks
The Gemini app now features Lyria 3, a music generation model that the source says can make 30-second tracks from text or images. The evidence does not compare it with the previous option, so the practical difference is not established.
The Gemini app now includes Lyria 3, which the source describes as its most advanced music generation model. According to the same page, the feature lets anyone make 30-second tracks using text or images. The source also says Lyria 3 is now available in the Gemini app and that users can create custom, high-quality 30-second tracks from text and images. That is the core of what is new: a music-generation tool inside Gemini, with two input routes and a fixed short output length.
What the evidence does not provide is a direct comparison with the previous option. The reader question asks what this can do that the previous option could not. The source calls Lyria 3 the most advanced model, but it does not list earlier capabilities, quality differences, controls, or limits beyond the 30-second length. So the practical answer is narrow: the source presents a new model in the app and a text-or-image way to generate short tracks. It does not state what was possible before, or what specifically changed for a user.
For everyday work, the immediate use is generating a short piece of music from a prompt or an image inside Gemini. The source does not state pricing, whether the feature is free or paid, whether tracks can be downloaded, edited, or used commercially, or whether the 30-second length is fixed in all cases. Those are open questions. The source's own description calls the tracks custom and high-quality, and it sets the length at 30 seconds. If you need longer music or detailed controls, the evidence does not say this provides them.
The practical takeaway is that a new music-generation capability is available in the Gemini app, with text and image inputs and a 30-second output. The comparison to what came before is not established in the material we have. That makes this a new capability worth noting, but not yet a fully explained upgrade.
Source details and supporting facts
Each line is stated by the page named above it.
Stated by deepmind.google
- The Gemini app now features Lyria 3, described as the most advanced music generation model.
- Lyria 3 lets anyone make 30-second tracks using text or images.
- Lyria 3 is now available in the Gemini app.
- Users can create custom, high-quality 30-second tracks from text and images.
Sources
- Google DeepMind blogText stored 15 September 2026
How this story was checked. Written from the 1 page listed above, stored 15 September 2026; claims checked against that stored text on 15 September 2026.
What that means
- 4 of 4 reported statements were confirmed against the page that carries them; the rest were removed rather than published.
- Figures in the text were required to appear in the stored source text: yes. Identifiers: yes.
- The check reads stored text only: no claim rests on a fresh look that did not happen.
- Where the reporting was silent, the text says so instead of filling the gap.