Lyria 3.5 generally available (GA)
By Steven Van ·
The Gemini API model now generates full songs with natural vocals and outputs 44.1 kHz stereo audio.
Lyria 3.5, the latest version of Google's music generation model, is now generally available through the Gemini API. It generates full-length songs with improved musical coherence and more natural vocals, plus fine-grained control over duration and song structure. The model takes text and image inputs and outputs high-fidelity 44.1 kHz stereo audio, with details and code samples in Google's music generation guide.
Google Gemini
Google's AI assistant — write, plan, brainstorm, generate images, and analyze files with one of the most powerful multimodal models.
View Google Gemini →