Lyria 3 is Google DeepMind's flagship AI music model, now live on Picsart's AI Playground. It generates full songs up to 3 minutes long with vocals, instrumentation, and professional-grade structure. From text prompts to image-to-music, Lyria 3 creates cohesive tracks across genres - pop, funk, Motown, and more. Every track is watermarked with SynthID for responsible AI identification. Flow integration coming soon.
Lyria 3 is the latest generation of Google DeepMind's music AI, built to understand musicality at a fundamental level - rhythm, arrangement, instrumentation, and vocal performance. The standard Lyria 3 generates polished 30-second tracks with lyrics, vocals, and full instrumentation. Lyria 3 Pro extends this to approximately 3-minute compositions with professional-grade structural awareness - verses, choruses, bridges, and outros that flow naturally. Both versions support multi-language vocals, genre-spanning creation, and detailed prompt control over every musical element. The model was developed with input from producers and musicians including Wyclef Jean and Yung Spielburg.
What you can create with Lyria 3
Describe the music you want - genre, mood, tempo, instruments, vocal style - and Lyria 3 produces a complete track with vocals, instrumentation, and professional structure up to 3 minutes long.
Lyria 3 generates music from text prompts — describe anything from "an upbeat birthday tune" to detailed specifications with tempo, key, and instrumentation preferences. Image-to-music converts uploaded images into custom soundtracks that match the visual mood. Define realistic vocal styles and acoustic preferences to shape your sound. Lyria 3 Pro adds full structural control: outline song progression in your prompt, control when lyrics start and end, and produce tracks with verses, choruses, and natural transitions up to 3 minutes. Every output receives SynthID watermarking for AI-origin detection.
Lyria 3 is now live on Picsart's AI Playground and will be available in Flow soon. Creators can generate AI music directly within Picsart and pair it with videos from AI Video Generator, creating complete audio-visual content without leaving the platform. This connects Lyria 3's music generation with Picsart's image and video tools for a unified creative workflow.
Lyria 3 stands out as the most musically aware AI model available. It understands song structure, not just sound generation. While other models produce short clips or loops, Lyria 3 Pro generates full 3-minute compositions with natural musical progression. Multi-language vocal support, genre versatility from classical to hip-hop, and prompt-level control over arrangement give creators professional-grade output from a text description. SynthID watermarking ensures responsible use, and the model's training on authorized materials means creators can use outputs confidently. Inside Picsart, it completes the creative loop: generate visuals, generate audio, publish - all in one place.
Lyria 3 is Google DeepMind's most advanced AI music generation model. It creates complete songs with vocals, instrumentation, and professional structure. Lyria 3 produces 30-second tracks, while Lyria 3 Pro generates full compositions up to approximately 3 minutes long.
Lyria 3 generates polished 30-second tracks with lyrics, vocals, and instrumentation. Lyria 3 Pro extends this to approximately 3-minute songs with full structural awareness — verses, choruses, bridges, and natural transitions — with control over when lyrics start and end.
Lyria 3 supports a wide range of genres including pop, funk, Motown, electronic, classical, hip-hop, R&B, rock, jazz, and more. It can also blend genres and create cross-genre compositions from text prompts.
Yes. Lyria 3 generates vocals in multiple languages with customizable vocal styles. You can define realistic vocal preferences, control lyric content, and specify when vocals start and end within a track.
Lyria 3 can convert uploaded images into custom music tracks that match the visual mood and atmosphere of the image. This is useful for creating soundtracks that complement visual content.
Every track generated by Lyria 3 is embedded with SynthID, Google DeepMind's imperceptible digital watermarking technology. This identifies the audio as AI-generated without affecting the listening experience.
Usage terms depend on the platform and access method. Through Picsart's integration, music generated with Lyria 3 can be used for creative and commercial projects subject to Picsart's terms of use.
Compare Lyria 3 with other audio models for music, sound, and creative production.
Generate AI visuals with Lyria 3
AI tools for everyday creative work.
Heavy AI usage for creators & teams.
Custom AI solutions for large organizations.
Learn how to compare image models and choose an output.
