On September 4, 2026, Google began providing the music generation model "Lyria 3.5" through the Gemini app and Gemini API. The model is said to enable high-fidelity music production through expressive vocals and rich arrangements. In the Gemini app, users can select genres, toggle between vocals and instrumentals, choose the length of the track, and utilize templates for purposes such as BGM or birthday songs. The service is available to all users worldwide via the web and mobile apps. Additionally, it will be provided through Google Flow Music for artists, and Google AI Studio and Google Vids for developers. Regarding API specifications, it supports instructions for lyric section structures, instrument control via timestamps, and music generation from images; it also provides text output of the generated lyrics and song structure. The pricing is $0.08 per song, with no free tier available.
Source: Google、音楽生成AI「Lyria 3.5」をGeminiアプリとAPIで提供開始 - innovaTopia (Google News: AI Copyright)