2 Sources
[1]
Google Introduces Lyria 3.5 for More Expressive AI-Generated Music
* Lyria 3.5 is claimed to create richer and more natural melodies * Users can better control song tempo and duration * Flow Music now offers more advanced editing tools Google has introduced Lyria 3.5, the latest version of its AI music generation model, with improvements aimed at making AI-created songs sound more natural and expressive. The update enhances melody generation, lyric quality, vocal performance and creative controls while expanding the ways users can shape their music. Lyria 3.5 is rolling out through Google Flow Music from today. The release builds on the company's earlier Lyria models and continues its efforts to improve AI-powered music creation. Google Lyria 3.5 Debuts With Improved Music Generation Features According to a Google blog post, the latest Lyria 3.5 model improves melody generation with more detailed compositions while producing lyrics that stay closer to user prompts and follow a more consistent song structure. Google also said the model produces more expressive vocals with improved pronunciation. Users can now exercise greater control over the tempo and duration of generated tracks through Flow Music. The launch also reflects Google's broader plans for Flow Music, which now offers more than simple AI song generation. The platform already lets users edit individual parts of a track, rewrite or translate lyrics, change instruments and refine music without recreating an entire composition. At Google I/O 2026, the company also introduced conversational editing tools for music videos and more precise controls for modifying individual elements within a track. Google first unveiled Lyria in 2023 as a music generation model from Google DeepMind before launching Lyria 3 earlier this year with support for creating songs from text prompts, images and videos. The model could also generate lyrics, vocals and cover art while allowing users to adjust the genre, mood and tempo. Google later released Lyria 3 Pro, extending song length to three minutes and adding more creative controls for paid Gemini subscribers. Lyria has since expanded to YouTube Shorts through Dream Track and to Google Vids for AI-generated background music. Google has not confirmed whether Lyria 3.5 will replace Lyria 3 Pro across Gemini or its developer platforms. The company also said Google AI Plus, AI Pro and AI Ultra subscribers receive access to different Flow Music subscription tiers.
[2]
Google Flow Music gets Lyria 3.5 with improved lyrics, vocals and creative controls
Google has introduced Lyria 3.5, its latest music generation model, in Google Flow Music. The new model brings improvements across musicality, lyrics generation, vocal quality and creative control. Lyria 3.5 improves AI music generation Lyria 3.5 introduces improvements across music creation, including composition, lyrics and vocals. The key updates include: * Improved musicality: Creates richer and more complex melodic structures that sound more natural. * Enhanced lyrics: Generates higher-quality lyrics with improved prompt adherence and structural awareness. * Improved vocals: Delivers more expressive and emotionally nuanced vocals with improved realism and pronunciation. The model also provides more creative control, allowing users to adjust the tempo and duration of generated music outputs. Google Flow Music features Google Flow Music includes features for creating, editing and sharing music. Users can create full-length songs, interact with Producer for studio-style conversations, and create music videos using the latest Veo video model with control over characters, aesthetics and visual details. The platform also includes Vibe-code Spaces, allowing users to build custom experiences such as audio plugins, music games and digital audio workstations (DAWs). Other features include remixing audio, applying audio effects, splitting stems, managing daily credits, creating playlists, publishing songs, following artists and discovering new music. Flow Music can also learn a user's creative style over time and personalize the experience based on their creations. Availability Lyria 3.5 is now available in Google Flow Music.
Share
Copy Link
Google has rolled out Lyria 3.5, an upgraded AI music generation model that delivers more natural melodies, expressive vocals, and better lyric quality. Available through Google Flow Music, the update gives users enhanced creative control over tempo and duration while introducing advanced editing tools for AI-powered music creation.
Google has unveiled Lyria 3.5, the latest iteration of its AI music generation model, bringing substantial improvements to how AI-generated music sounds and how users interact with the creative process. Rolling out through Google Flow Music starting today, the update focuses on delivering richer melodies, higher-quality lyrics, and more expressive vocals while expanding creative control options
1
. The release marks another step in Google's ongoing efforts to refine AI-powered music creation and make it more accessible to users seeking natural-sounding compositions.
Source: Gadgets 360
According to Google's announcement, Lyria 3.5 introduces improvements across multiple dimensions of music creation. The AI music generation model now produces more complex melodic structures that sound notably more natural compared to previous versions
2
. For those working with text prompts, the model generates lyrics that adhere more closely to user instructions while maintaining consistent song structure throughout compositions1
. The enhanced vocal performance delivers emotionally nuanced singing with improved pronunciation and vocal realism, addressing one of the persistent challenges in expressive AI-generated music2
.Beyond audio quality improvements, Lyria 3.5 offers users enhanced creative control over their generated tracks. Musicians and creators can now adjust tempo and duration with greater precision, allowing for more deliberate shaping of their compositions
1
. This level of control addresses a common limitation in earlier AI music tools where outputs felt rigid or difficult to customize.Google Flow Music has evolved beyond simple song generation into a comprehensive platform for music creation and editing. Users can now edit individual parts of a track, rewrite or translate lyrics, change instruments, and refine music without recreating entire compositions
1
. The platform includes a Producer feature that enables studio-style conversations, and integrates the Veo model for music video generation with detailed control over characters, aesthetics, and visual elements2
. Additional capabilities include remixing audio, applying audio effects, and stem splitting for isolating individual instrumental or vocal tracks2
.Google first introduced Lyria in 2023 as a music generation model developed by Google DeepMind, before launching Lyria 3 earlier this year with support for creating songs from text prompts, images, and videos
1
. That version could generate lyrics, vocals, and cover art while allowing users to adjust genre, mood, and tempo. Google later released Lyria 3 Pro, which extended song length to three minutes and added more creative controls specifically for paid Gemini subscribers1
. The technology has since expanded to YouTube Shorts through Dream Track and to Google Vids for AI-generated background music.Google has not confirmed whether Lyria 3.5 will replace Lyria 3 Pro across Gemini or its developer platforms, leaving questions about how the model will integrate into Google's broader AI ecosystem
1
. The company noted that Google AI Plus, AI Pro, and AI Ultra subscribers receive access to different Flow Music subscription tiers, suggesting a tiered approach to feature availability.Related Stories
The improvements in melody generation and vocal quality address critical gaps that have prevented AI music tools from achieving widespread adoption among serious creators. By offering better prompt adherence and structural awareness in lyrics, Lyria 3.5 reduces the trial-and-error often required to achieve desired results. The platform's ability to learn a user's creative style over time and personalize the experience based on their creations suggests Google is building toward more intuitive, adaptive tools
2
. As AI music generation continues to mature, the focus on creative control and editing flexibility may prove essential for bridging the gap between AI assistance and human artistry.Summarized by
Navi
25 Mar 2026•Technology
19 May 2026•Technology

18 Feb 2026•Technology

1
Technology

2
Technology

3
Technology
