{
  "id": 6489263,
  "title": "Google Lyria 3.5 Brings Music Controls and Templates to Gemini Creators",
  "url": "https://urgent.news/2026/09/09/google-lyria-3-5-brings-music-controls-and-templates-to-gemini",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-09T22:45:30.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/alifar/google-lyria-35-brings-music-controls-and-templates-to-gemini-creators-5202"
  },
  "original_language": "en",
  "account": "Google has launched Lyria 3.5 within the Gemini app and Gemini API, offering creators greater control over AI-generated music. This update allows users to specify duration, tempo, genre, vocals, lyrics, and song structure. A template gallery is also provided for faster experimentation. For businesses generating video, social, product, or presentation content, this means more precise music generation that aligns with their defined format and brief. Google describes Lyria 3.5 as an improvement in musicality and vocal fidelity. Users can now create vocal or instrumental tracks, choose genres and vocal styles, adjust track length, and start with templates. The release is also available via the Gemini API, allowing developers to integrate music generation into their tools and workflows. The core enhancement in Lyria 3.5 is not just the model's ability to generate music, but the increased ability to specify the output. Users can provide instructions that direct the track's progression through sections such as verses, choruses, and bridges. The Gemini API also supports text and image inputs through the Interactions API, enabling an image to serve as creative context for music generation. Notable controls and output options include tempo and duration adjustments, vocal and instrumental choices, lyrics with multilingual support, and structured prompting for guiding musical sections. The Pro model generates tracks up to two minutes long, while the user interface allows tracks up to about three minutes. At 44.1 kHz stereo, Lyria 3.5 outputs up to approximately three minutes of audio. The API's Pro model output lasts about a couple of minutes. Lyria 3.5 is accessible through the Gemini app, Gemini API, Flow Music for artists and AI creatives, Google Vids, and AI Studio integrations. For users utilizing the Gemini API, Google charges $0.08 per full song and $0.04 for a 30-second clip. These pricing points provide a clearer cost basis for testing compared to an open-ended estimate. However, generated content must still be assessed for suitability with the intended campaign, audience, and creative direction. Produced content is watermarked with SynthID, Google's identification system for AI-generated media, aiding teams in distinguishing generated assets within their creative process.",
  "summary": "Google has released Lyria 3.5 across the Gemini app and Gemini API, adding more direct control over how AI-generated music is shaped. The update gives creators options for duration, tempo, genre, vocals, lyrics, and song structure, while a template gallery offers starting points for faster experimentation. For businesses producing video, social, product, or presentation content, the practical…",
  "key_points": [
    "Lyria 3.5 allows users to specify duration, tempo, genre, vocals, lyrics, and song structure.",
    "Template gallery provided for faster experimentation in music generation.",
    "Pricing at $0.08 per full song and $0.04 for a 30-second clip via Gemini API."
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}