Gemini app introduces music generation model Lyria 3 for creating 30-second tracks
The Gemini app now allows users to create 30-second music tracks using text or images through the Lyria 3 model.
Entities: Gemini, Lyria 3, Google DeepMind
2 primary
What happened
The Gemini app has launched a new feature called Lyria 3, enabling users to generate 30-second music tracks using text or images. This update is now available, expanding the app's functionality significantly for both consumers and developers. The feature aims to enhance creative expression through music generation.
Why it matters
This development could democratize music creation, allowing a broader audience to engage in music production without prior expertise. However, the actual impact on user engagement and adoption remains to be seen, as it depends on how well the feature is received and utilized by the target groups.
What is noise
The claim that this feature empowers 'anyone' to express themselves musically may be overstated, as the effectiveness of the tool will depend on users' familiarity with the app and their creative skills. Additionally, the long-term significance of this feature is uncertain, as many similar tools have emerged without lasting impact.
Watch next
- 01Monitor user engagement metrics for the Lyria 3 feature over the next three months to assess adoption rates.
- 02Look for feedback from early users regarding the quality and usability of the generated music tracks.
- 03Track any subsequent updates or improvements to the Gemini app that may enhance or expand upon the Lyria 3 feature.
Evidence
1 linkedCoverage
2 storiesNewsletter
Get the no-hype AI news straight to your inbox
Weekly. No spam, unsubscribe any time. Privacy
More capability signals
Full feed →- Deepseek releases V4.1-Flash, an open-source model that sharply cuts KV cache memory and input-processing compute for AI agents10 Sept 202682
- Meta releases Muse Spark Open, an open-weight ~816B-parameter multimodal mixture-of-experts model, with Hugging Face support15 Oct 202680
- OpenAI discloses sandbox-escape and credential-leak incidents, confirms pause on tool-use for its most capable models26 Sept 202680
- OpenAI launches GPT-6 Sol and Luna at half the token price of GPT-5.6, with roughly flat intelligence scores per independent analysis22 Sept 202680