Lyria 3.5
Lyria 3.5 is Google's newest music generation model, with richer melodies, better lyrics, more expressive vocals, and easier control over tempo and length. This page tracks what changed, where you can actually use it, and how it compares with Lyria 3 — and lets you generate a track here with Lyria 3 Pro.
Generate music with Lyria 3 Pro on this site
Lyria_3_Pro_Demo_Output.mp4
Built-in demo preview
What's New in Lyria 3.5
Lyria 3.5 is Google DeepMind's most capable music generation model to date, improving melody, lyrics, vocals, and creative control over earlier Lyria models.
Richer Melodic Structures
Lyria 3.5 writes richer, more complex melodic structures that sound more natural across a full track, rather than looping a single idea until the clip ends.
Higher Quality Lyrics
Lyria 3.5 improves prompt adherence and structural awareness in lyrics, so verses and choruses follow the brief you actually wrote instead of drifting off topic.
More Expressive Vocals
Lyria 3.5 delivers more realistic and emotionally nuanced vocals with improved pronunciation — the single most contested area in earlier Lyria releases.
Easier Tempo and Length Control
Lyria 3.5 makes tempo and duration easier to steer, so a 60-second cue, a half-length edit, or a full three-minute song comes from the prompt itself.
Lyria 3.5 Capabilities for AI Music Generation
Lyria 3.5 combines full-length song structure, multi-language vocals, granular prompt control, and SynthID watermarking on every track.
Tracks Up to Three Minutes
Lyria 3.5 reaches about three minutes, long enough for a complete arrangement with intro, verse, chorus, and bridge instead of a short repeating loop.
Vocals in Multiple Languages
Lyria 3.5 generates sung vocals in different languages and specifically targets clearer pronunciation — a known weak point for non-English lyrics.
Prompt Down to BPM and Key
Lyria 3.5 prompts accept genre blends, tempo, instrumentation, dynamics, key, and a vocal profile covering gender, range, texture, and language.
Song Structure Tags
The Lyria 3 API accepts structure tags such as Verse, Chorus, Bridge, Intro, and Outro, or timestamps, to control how the song progresses.
Image and Video to Music
Lyria can turn an uploaded image or video into a matching high-fidelity track, scoring the tone and pacing of the reference you provide.
SynthID Watermark on Every Track
Google applies an inaudible SynthID watermark to all Lyria 3.5 output, so a track can be identified as AI generated without affecting how it sounds.
Lyria 3.5 vs Lyria 3, Lyria 3 Pro, and Lyria RealTime
Lyria 3.5 is the newest model in the family, but it is not simply a renamed Lyria 3 Pro — the distribution and API picture is different. Verified against Google model cards on July 31, 2026.
| Model | Track length | API model id | Where Google lists it |
|---|---|---|---|
| Lyria 3.5 (July 29, 2026) | Up to about 3 minutes | No public API model id yet | Google Flow Music only |
| Lyria 3 Pro | A couple of minutes, promptable | lyria-3-pro-preview | Gemini API, Vertex AI, AI Studio, Gemini app and more |
| Lyria 3 Clip | Fixed 30 seconds | lyria-3-clip-preview | Gemini API, Vertex AI, AI Studio, Gemini app and more |
| Lyria 2 | Shorter instrumental output | Superseded by Lyria 3 | Legacy, used as the benchmark baseline for Lyria 3.5 |
| Lyria RealTime | Continuous, never-ending stream | Separate realtime product line | A different product line, not a version of Lyria 3.5 |
Where to Use Lyria 3.5
Google Flow Music is the only product listed in the Lyria 3.5 model card, so the newest model is narrower in reach than Lyria 3 — here is what each entry point actually gives you.
Google Flow Music
Google Flow Music is the only place Google lists Lyria 3.5 today. Formerly Producer AI, it adds songs, playlists, and music video tools around the model, and is the entry point to try Lyria 3.5 itself.
Gemini App
The Gemini app runs Lyria 3 rather than Lyria 3.5, free for eligible users, with the Pro model reserved for paid Google AI tiers. Pick the Pro model if you want more than a 30-second clip.
Gemini API and Vertex AI
Developers reach Lyria through lyria-3-clip-preview and lyria-3-pro-preview, billed per generated track. No Lyria 3.5 model id has been published, so production integrations still run on Lyria 3.
This Site
The generator on this page runs Lyria 3 Pro, the strongest Lyria model currently exposed through the API. Write a prompt, pick vocals or instrumental, and download the track.
How to Use Lyria 3.5 and Lyria 3 Pro
Three steps from a music idea to a downloadable track, whether you are testing Lyria 3.5 in Flow Music or generating here with Lyria 3 Pro.
Write a Detailed Prompt
Name the genre, mood, tempo in BPM, key, instruments, and vocal profile. Specific prompts beat long conflicting ones, and Lyria 3.5 targets exactly this kind of prompt adherence.
Set Length and Vocals
Ask for a 60-second cue, a half-length edit, or a full three-minute song, and choose instrumental or vocal mode with the lyric language you want.
Generate, Review, Download
Generate the track, listen back, refine the prompt if the structure drifts, then download the audio for your video, podcast, or DAW session.
Should You Switch from Lyria 3 to Lyria 3.5?
Google describes four improvements in Lyria 3.5, but several long-standing limitations were not mentioned in the announcement — worth checking before you move a workflow.
Improved: Vocals and Pronunciation
Vocal realism was the loudest complaint about earlier releases, and it is one of the four areas Google explicitly says Lyria 3.5 improves, along with pronunciation.
Improved: Prompt Adherence
Lyrics with better prompt adherence and structural awareness address the recurring problem of dropped lines and repeated phrases in generated songs.
Not Addressed: Editing an Existing Track
Music generation through the Lyria 3 API is single-turn, and iterative editing of a generated clip is not supported. The Lyria 3.5 announcement does not claim to change this.
Not Addressed: API Access
Lyria 3.5 has no published API model id, pricing, or rate limits. If you build on the API, Lyria 3 Pro remains the model you can actually ship with today.
Pricing
Subscribe or pay-as-you-go - flexible plans to fit your needs. Cancel subscription anytime
Starter
- 12,000 credits per year
- Media-to-Music (Text / Lyrics / Image / Video / Audio)
- Full vocal generation
- Lyrics generation
- Cover art generation
- Commercial Use License
- Email support
- Cancel anytime
Standard
- 36,000 credits per year
- Media-to-Music (Text / Lyrics / Image / Video / Audio)
- Full vocal generation
- Lyrics generation
- Cover art generation
- Commercial Use License
- Priority support
- Cancel anytime
Pro
- 78,000 credits per year
- Media-to-Music (Text / Lyrics / Image / Video / Audio)
- Full vocal generation
- Lyrics generation
- Cover art generation
- Commercial Use License
- 24/7 support
- Cancel anytime
Lyria 3.5 FAQ
Answers on the Lyria 3.5 release, what changed from Lyria 3, where it runs, API availability, watermarking, and commercial rights.
Lyria 3.5 is Google DeepMind's newest music generation model, described by Google as its most capable music model to date. It turns a written prompt into a full track with sung lyrics, reaching about three minutes in length, and every output carries an inaudible SynthID watermark.
Google announced Lyria 3.5 on July 29, 2026, rolling it out in Google Flow Music. The model card carries the same publication date, making it roughly five months newer than Lyria 3, which was published in February 2026.
Google lists four improvements: richer and more natural melodic structures, higher quality lyrics with better prompt adherence and structural awareness, more realistic and emotionally nuanced vocals with improved pronunciation, and easier control over tempo and duration. Google has not published a numeric comparison against Lyria 3, and the model card benchmarks Lyria 3.5 against Lyria 2 instead.
Google Flow Music is the only product listed in the Lyria 3.5 model card. This is narrower than Lyria 3, whose model card lists the Gemini app, Vertex AI, AI Studio, Google Vids, YouTube, Producer AI, and Music AI Sandbox. The generator on this page runs Lyria 3 Pro.
No. As of July 31, 2026 the Gemini API music documentation lists only lyria-3-clip-preview and lyria-3-pro-preview, with no Lyria 3.5 model id, pricing, or rate limits published. Developers building today still integrate Lyria 3.
Google states that it does not claim ownership of the original content generated with Flow Music, which is not the same as a blanket commercial licence — your rights also depend on the platform terms and plan you generate under. Separately, every Lyria 3.5 track carries a SynthID watermark that is inaudible to listeners but lets the audio be identified as AI generated.
Lyria 3.5 applies Google's generative AI usage policies and filters prompts at generation time, so lyrics naming specific recording artists or reproducing copyrighted words are commonly rejected or rewritten. Rewriting the prompt in your own words is the reliable fix; there is no supported way to bypass the filter.
Switch if vocal quality, pronunciation, and lyric accuracy are your bottleneck, since those are the areas Google says Lyria 3.5 improves. Stay on Lyria 3 Pro if you need API access, since Lyria 3.5 has no published model id, or if your workflow depends on editing generated tracks, which Lyria's single-turn generation does not support.
Generate a Track with Lyria 3 Pro
Write a prompt, pick vocals or instrumental, and download your track — powered by Lyria 3 Pro, the newest Lyria model available through the API while Lyria 3.5 stays inside Google Flow Music.