Skip to content

Lyria 3.5 generally available (GA)

GAVerifiedAdded Sep 22, 2026

Released the next generation of Google's music generation model: lyria-3.5: Full-length song generation with improved musical coherence, natural vocals, and fine-grained duration and structural control. The model supports text and image inputs and generates high-fidelity 44.1 kHz stereo audio. See the Music generation guide for details and code samples.

Read Google Cloud's release notes

https://ai.google.dev/gemini-api/docs/changelog#september-3-2026

Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.

More Gemini API releases

Gemini API

Gemini 3.8 Flash generally available (GA)

GA
Gemini API

Agentic video understanding

Update
Gemini API

Gemini Omni Flash generally available (GA)

GA
Gemini API

Gemini 3.5 Transcribe generally available (GA)

GA
Gemini API

Antigravity Agent 09-2026

Preview
Gemini API

Gemini 2.5 models access update

Update
Gemini API

Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS generally available (GA) : Released our next-generation

GAUnverified

Also shipped on Sep 3, 2026

Genie One enhancements

Preview

Web search in Genie One (Beta)

Beta

Workspace Outbound Access Protection (OAP) for Operations Agent and Fabric Maps (Preview)

Preview

Weekly: the week's data and AI releases, Tuesday mornings.