Lyria 3.5 — Google DeepMind

Our most advanced music generation model, now up to 3 minutes long
Compose with freedom and technical control. Define realistic vocal styles and acoustic preferences to find the sound you’re looking for.
Generate cohesive tracks matching your project's exact duration — whether you need a quick 60-second clip, a half-length track, or a full 3-minute song.
Upload an image and ask Lyria to transform it into a custom high-fidelity track.
Our newest music generation model delivers significant advancements across musicality, lyrics, and vocal quality, empowering you to craft richer tracks.
Prompt: funk pop, electropop, hyperpop, funk bass, electric guitar, female vocal, 95 bpm
Prompt: Full 3-minute Bossa-Trip-Hop track with a heavy 82 BPM MPC-swung drum groove, UK electronic/glitch design, and clean vocal separation.
Prompt: upbeat and energizing Spanish dance pop and reggaeton track
Prompt: Stylish French alternative pop with warm analog synths, a groovy rounded bassline, soft funk guitar, and airy disco-tinged drums. 110 BPM, B minor. Breathy, elegant female vocal front and center, half-whispered verses opening into a smooth melodic chorus, delicate stacked harmonies, effortless and cool.
Prompt: neosoul, rnb, deep male baritone vocal, groovy pocket, chill, slow sensual, rhodes keys
Prompt: electronica, hard groove, glitch hop, electropop, funk bass, female vocal, 90 bpm
Prompt: Brazilian funk carioca 130–135 BPM rhythm
Prompt: Reggaeton, Dembow, Neoperreo with distorted synthesizers, lo-fi aesthetics, Chilean vocal style, female empowerment
Prompt: Hindi singer songwriter male indie - delicate, acoustic guitar, light percussion, strings
Prompt: Afro-pop jazz fusion over Caribbean grooves: syncopated calypso percussion, steel pan accents, warm horn section, melodic walking bassline, jazzy seventh chords on keys. 108 BPM, F major. Playful male vocal with jazz phrasing and light scat runs front and center, horns answering each line, rich layered chorus harmonies.
Prompt: glitch electronica, chopped stuttering percussion, soft clicks, vinyl dust, warm evolving pads, soft airy female vocal, phrases sliced and re-pitched into glitch textures, breathy sustained notes
Lyria helps you express, explore, and experiment with high-fidelity music, using prompts to create tracks with natural flow from note to note.
Fine-tune the details and generate professional-grade audio with Lyria. Our family of music generation models can create clips and tracks, or deliver a constant stream of music.
Our latest model with improved vocals, musicality, and variable song lengths
Explore new genres, play with soundscapes, and find musical inspiration
Designed for real-time, interactive music generation.
Our Lyria open model explores the role of machine learning as a tool in the creative process.
Lyria is our most advanced AI music generation tool. We’ve developed it with input from producers and musicians so it understands musicality – from rhythm to arrangement.
Describe your track, then dial in the details you want. Lyria handles the complexity, putting new musical possibilities at your fingertips.
Turn quick ideas into high-fidelity music that flows naturally from start to finish, up to 3 minutes long.
Generate vocals in different languages, and create music spanning genres from pop to funk to Motown.
Upload an image and ask Lyria to transform it into a custom high-fidelity track.
Compose with freedom and technical control. Define realistic vocal styles and direct the details to find the sound you’re looking for.
Background ambience or mainstage anthem – produce crisp, clear tracks ready for your projects.
Keep it simple with a rough idea of what you want – like ‘an upbeat birthday tune’. Or describe the details for more control, like tempo and dynamics. Don’t forget to experiment as you go.
Create pieces in countless styles using Lyria.
Lyria takes images and turns them into music.
Write your own lyrics, or generate them around specific subjects or themes. Then express them with realistic, natural, and nuanced vocals.
See how our artists partners are experimenting with AI
Legendary producer Wyclef Jean gets hands on with a new style of creative expression. Watch Wyclef produce, curate and design alongside Music AI Sandbox.
Scoring the animated short Dear Upstairs Neighbors, Yung Spielburg leant on Lyria to move beyond the limits of traditional instrumentation. The result is a collection of signature, sonic timbres that are not just unique, but technically impossible to manifest by any other means.
We believe AI should enhance human creativity, not replace it. We’re working directly with artists to gather feedback and shape guardrails that address their concerns. By doing this, we ensure this tool empowers creators and helps them realize the possibilities of AI in their work.
We use extensive filtering and data labeling to minimize harmful content in datasets and reduce the likelihood of harmful lyrics. Audio generation in Lyria has our latest privacy and safety features. All of our tracks are imperceptibly watermarked with SynthID technology, allowing you to detect whether music has been created or edited using AI.
While Lyria can create a wide range of music, we’re still working on improving key capabilities. You should always carefully check that the tracks you create fit your vision.
Built with, and for, musicians