Google launches Lyria 3 Pro, extending AI music generation to 3-minute tracks
Google announced Lyria 3 Pro, an upgraded music generation model capable of creating tracks up to three minutes long—a tenfold increase from Lyria 3's 30-second maximum. The model adds structural music understanding (intros, verses, choruses, bridges) and rolls out to Gemini app paid subscribers, Google Vids, ProducerAI, and enterprise tools including Vertex AI, the Gemini API, and AI Studio.
Google launches Lyria 3 Pro, extending AI music generation to 3-minute tracks
Google has released Lyria 3 Pro, a music generation model that extends track length from 30 seconds to 3 minutes and adds structural understanding of musical composition, according to an announcement on Wednesday.
The new model improves upon Lyria 3—released one month prior—by allowing users to specify discrete musical elements in prompts, including intros, verses, choruses, and bridges. Google claims the model demonstrates improved understanding of track structure compared to its predecessor.
Availability and Integration
Lyria 3 Pro rolls out across multiple Google products and platforms:
- Gemini app: Exclusive to paid subscribers
- Google Vids: Video editing application
- ProducerAI: Music production tool acquired by Google last month
- Enterprise tools: Vertex AI (public preview), Gemini API, and AI Studio
Google previously integrated music generation into Gemini following Lyria 3's release. The Pro model extends this capability to enterprise customers via Vertex AI and API access.
Training Data and Attribution
Google states that Lyria 3 Pro was trained using data from partners, permissible YouTube content, and Google-owned data. The company claims the model does not directly mimic specific artists but takes "broad inspiration" when users specify artist names in prompts.
All tracks generated by Lyria 3 and Lyria 3 Pro are marked with SynthID, Google's watermark indicating AI-generated content. This labeling emerges as the music industry implements identification and authentication mechanisms. Earlier this week, Spotify released artist review tools to prevent AI-misattributed music, while Deezer launched detection tools for streaming services to identify AI-generated content.
What this means
Lyria 3 Pro represents Google's competitive response to growing demand for AI music generation—a space where Suno and Udio have gained significant traction. The extension to 3-minute tracks removes a primary limitation preventing professional music production use cases. Enterprise access via Vertex AI and APIs signals Google's strategy to monetize music generation through B2B channels rather than consumer subscriptions alone. The emphasis on SynthID marking and structural composition control suggests Google is prioritizing artist protection and production-quality features over maximum creative automation, positioning Lyria against pure-generation competitors.
Related Articles
Xiaomi's MiMo-V2.6-Pro Becomes Top Open-Weights Model, Trained for $3M According to Xiaomi
Xiaomi released MiMo-V2.6-Pro, a 1.02T-parameter mixture-of-experts model with 42B active parameters, which debuted as the top-scoring open-weights model on Artificial Analysis' Intelligence Index (46). The company claims the model's RL training run cost roughly $2.6M and completed in 130 hours.
Xiaomi Releases MiMo-V2.6-Pro-RL, a 1.02T-Parameter Omnimodal Model with 1M-Token Context
Xiaomi's MiMo team has released MiMo-V2.6-Pro-RL, a 1.02-trillion-parameter sparse mixture-of-experts model with 42B active parameters, 1M-token context, and native text/image/video/audio processing. The model was trained via a single mixed reinforcement learning run spanning coding, agentic, visual, and cybersecurity tasks, with benchmark scores that Xiaomi claims approach or match Claude Opus 5 and GPT-5.6 on several agentic and coding tests.
Xiaomi Releases MiMo-V2.6-Flash-RL, a 309B-Parameter MoE Model with 1M-Token Context and Native Omnimodal Support
Xiaomi's MiMo team released MiMo-V2.6-Flash-RL, an efficiency-tier checkpoint in the MiMo-V2.6 series featuring a 309B-parameter (15B active) Mixture-of-Experts architecture, 1M-token context, and native support for text, image, video, and audio. The model uses a single mixed reinforcement learning run across coding, agentic, visual, and cybersecurity tasks rather than domain-specific training.
TypeSafe AI Launches Jev, a 'Decision Model' That Outputs Only Numbers, Priced at $0.042/M Input Tokens
TypeSafe AI has released Jev, the first model in a new category it calls 'System One models'—text goes in, floating-point decisions come out. At $0.042 per million input tokens with free output, it undercuts even GPT-5 Nano on price.
Comments
Loading...