Google introduces new AI music generation model Lyria 3, providing high-quality audio with a single prompt..
Google DeepMind announced its latest artificial intelligence (AI) music generation model, Lyria 3, on Wednesday. According to the Mountain View tech company, the new model is integrated into the Gemini app for Android and iOS and is designed to help users create high-quality music tracks using simple text prompts using multimodal generative AI. Lyria 3 is billed as a creator-focused tool aimed at simplifying music production for social media, video, and digital storytelling.
Lyria 3 Features
Google DeepMind explained in a blog post that Lyria 3 provides new music creation capabilities within the Gemini app. Users can create original tracks up to 30 seconds long by specifying their preferred genre, mood, tempo, or instruments. The music generation model translates text prompts into fully produced audio clips, featuring layered instrumentation and a polished sound output.
Compared to the previous version, Lyria 3 boasts several enhanced capabilities. First, it can automatically generate lyrics based on prompts, while also offering greater control over elements like style, vocals, and tempo. Furthermore, it offers improved audio quality, better instrumentation, and better coherence in longer compositions.
In addition to text-to-track creation, Lyria 3 in Gemini allows users to create music inspired by photos and videos. For example, sunset images or short travel clips can be used as creative input, with Lyria 3 creating a soundtrack that matches the visual tone and atmosphere. Each created track can also include custom AI-generated cover art, making it easier for creators to package and share their work.
Google is also extending Lyria's capabilities to YouTube Dream Track, where users can experiment with AI-generated music for Shorts and other content formats. Dream Track helps creators explore different musical styles and themes using similar generative AI technology.
To address concerns about the authenticity of AI-generated media, Google has embedded its SynthID watermarking technology into Lyria 3 output. This invisibly marks the generated audio with metadata that helps identify it as AI-created content for transparency and responsible use.
The company also stated that this model is part of its larger push towards multimodal AI, where text, image, audio, and video generation occur together on a unified platform.
According to the tech giant, Lyria 3 is available in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese in the Gemini app on desktop for all users over the age of 18. Its rollout to the Gemini app for Android and iOS will occur in the next few days. Google AI Plus, Pro, and Ultra subscribers can avail higher limits.
Disclaimer: This content has been sourced and edited from Dainik Jagran. While we have made modifications for clarity and presentation, the original content belongs to its respective authors and website. We do not claim ownership of the content.
