Lyria 3.5
Lyria 3.5 is a next-generation music generation model that produces full-length songs with improved musical coherence and natural-sounding vocals. It accepts text and image inputs and outputs high-fidelity 44.1 kHz stereo audio.
What it does
Can be used to generate complete music tracks from text or image prompts, with control over duration and structure.
- Availability
- GA (2026-09-03)
- Pricing model
- Not established
- Deployment
- hosted via Gemini API
- Privacy
- Not established
- Licence
- Not established
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- Generates full-length songs. [1]
- Produces natural-sounding vocals. [1]
- Provides fine-grained duration and structural control for generated music. [1]
and fine-grained duration and structural control.
Google. Quoted text is outside CC BY 4.0 and keeps its original rights. - Accepts text and image inputs (multimodal prompts). [1] [2]
The model supports text and image inputs and generates high-fidelity 44.1 kHz
Google. Quoted text is outside CC BY 4.0 and keeps its original rights. - Outputs high-fidelity 44.1 kHz stereo audio. [1]
The model supports text and image inputs and generates high-fidelity 44.1 kHz
Google. Quoted text is outside CC BY 4.0 and keeps its original rights. - Released to general availability (GA) on 2026-09-03 via the Gemini API.
Sources
2
1
GoogleOwner-controlled
https://ai.google.dev/gemini-api/docs/changelog#2026-09-03
Retrieved 2026-10-28 00:27 UTC
Verified
2
GoogleOwner-controlled
https://blog.google/innovation-and-ai/technology/ai/google-ai-updates-september-2026/
Retrieved 2026-10-28 00:27 UTC
Verified
Versions
3| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 3 | 2026-10-17 07:00 UTC | evidence update | score | Current |
| 2 | 2026-10-03 19:51 UTC | evidence update | score | Current |
| 1 | 2026-09-03 00:00 UTC | publication | None | Current |
In briefs
2- WeatherNext 2 leads 13 AI developments in week 36, 2026 Weekly brief 2026-W36
- Lyria 3.5 from Google, the one AI development on 3 September 2026 Daily brief 2026-09-03
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.