Google Launches AI Music Model Lyria 3.5, Integrates into Flow Music to Enhance Musicality and Creative

Google has launched its next-generation AI music generation model Lyria 3.5, simultaneously integrating it into Flow Music, the AI music creation tool under Google Labs. The new model focuses on upgrading musicality, lyrics generation, AI vocals, and creative control, allowing users to generate songs that are more natural, structurally complete, and emotionally rich. This update marks a significant step in Google's continuous iteration in the AI music field, aiming to strengthen the ability to generate complete songs from text.

Lyria 3.5 is upgraded in four main areas. In terms of musical expressiveness, the new model can generate more complex melodic structures, making the overall music more natural and fluid, with song arrangements that better align with real music creation logic. For lyrics generation, the model has improved prompt comprehension, enabling it to more accurately understand user requests and produce lyrics with better structure and higher quality. AI vocals represent the biggest upgrade: the new model generates vocals with more natural and emotionally expressive singing, while also improving pronunciation accuracy. Additionally, users can more precisely control song tempo and generation length, further enhancing creative freedom.

In terms of creative control, Flow Music aims to make AI more like a creative partner. Users can continuously modify songs through natural language prompts, iterating on melody, lyrics, style, tempo, and overall atmosphere without needing to regenerate the entire song each time. Lyria is a series of AI music generation models developed by Google DeepMind. In February 2026, Google launched Lyria 3; in late March, it released Lyria 3 Pro, extending the maximum song generation duration to 3 minutes and supporting user-defined song structures such as intro, verse, chorus, and bridge. With the release of Lyria 3.5, no new benchmark scores were disclosed, with the upgrade focus placed on user experience aspects such as vocal quality, lyric creation, and creative control.

In recent years, AI music has become a key direction in the generative AI competition. Besides Google, startups such as Suno and Udio have rapidly emerged, while OpenAI continues to explore multimodal content generation capabilities. As an important component of Google Labs' creative tools portfolio, Flow Music, together with the Flow video generation platform, is building Google's AI content creation ecosystem. With the launch of Lyria 3.5, Google is further integrating AI capabilities into the entire music creation process, covering the complete workflow from creative ideation and lyric writing to song generation and editing.