New Delhi: Google has introduced Lyria 3.5, the latest version of its AI-powered music generation model, bringing significant improvements to melody creation, vocals, lyrics and creative controls. The model is rolling out through Google Flow Music, the company’s AI music creation platform, allowing users to generate richer and more expressive songs from simple prompts.
The launch builds on Google’s earlier Lyria models developed by Google DeepMind and reflects the company’s continued investment in generative AI tools for music creators.
Lyria 3.5 focuses on more natural music
According to Google, Lyria 3.5 produces more detailed and natural-sounding melodies while improving lyrical quality and vocal performance.
The company said the updated model better understands user prompts, resulting in songs with more coherent structures and lyrics that remain closer to the requested theme. Google also claims that vocals now sound more expressive, emotional and feature improved pronunciation.
Greater creative control for users
One of the biggest upgrades in Lyria 3.5 is the addition of enhanced creative controls.
Users can now adjust the tempo, duration and other musical elements more precisely while creating songs in Flow Music. These tools are designed to help musicians and creators fine-tune AI-generated tracks without repeatedly starting from scratch.
Flow Music gains advanced editing tools
Google is also expanding the capabilities of Flow Music beyond simple song generation.
The platform already enables users to edit individual parts of a song, rewrite or translate lyrics, switch instruments and refine specific sections of music instead of regenerating an entire composition. At Google I/O 2026, the company also introduced conversational editing features and more precise controls for modifying music videos and audio elements.
Built on previous Lyria models
Google first introduced Lyria in 2023 before launching Lyria 3 earlier this year.
Lyria 3 supported AI-generated songs from text prompts, images and videos while offering AI-generated lyrics, vocals and cover art. Google later released Lyria 3 Pro, extending the maximum song length to three minutes and providing additional creative controls for paid Gemini subscribers. Lyria 3.5 now builds on those capabilities with improvements across musicality and user control.
Availability
Google confirmed that Lyria 3.5 is rolling out through Flow Music beginning this week.
The company has not yet announced whether the new model will immediately replace Lyria 3 Pro across Gemini or its developer platforms. Different subscription tiers of Google AI Plus, AI Pro and AI Ultra will continue to determine access to Flow Music features.
AI music competition intensifies
The release of Lyria 3.5 comes as competition in AI-powered music generation continues to grow.
Google’s latest update aims to compete with other AI music platforms by offering more realistic vocals, stronger prompt adherence and improved editing capabilities for creators producing music with artificial intelligence.
Conclusion
With Lyria 3.5, Google is pushing further into AI-assisted music creation by delivering more natural vocals, richer melodies and improved creative controls. As the model rolls out through Flow Music, creators will gain access to more sophisticated tools for composing, editing and refining AI-generated songs.