Google Gemini: Taking another big step in the world of Artificial Intelligence, Google DeepMind has launched its new music generation model Lyria 3.
Google Gemini: Taking another major step in the world of artificial intelligence, Google DeepMind has launched its new music generation model, Lyria 3. According to the company, this advanced AI model will now be available to Android and iOS users through the Gemini app. Its goal is to create excellent music tracks using simple text instructions.
Lyria 3 is specifically designed for creators who want to quickly create professional-sounding music for social media, video, or digital storytelling. It's based on multimodal generative AI technology, meaning it can understand various inputs like text, images, and video to create audio.
The entire song will be prepared from the text.
Using Lyria 3 within the Gemini app, users can create original music tracks of up to 30 seconds. Simply specify the desired genre, mood, tempo, and instruments. The model interprets these instructions and creates a finished audio clip that includes background music, layered instruments, and a balanced sound output.
Smarter and more controlled than ever before
The company claims that Lyria 3 is more advanced than its predecessor. It can now automatically generate lyrics based on input. It also offers users greater control over aspects like style, vocal tone, and tempo. It also boasts improved sound quality and the ability to maintain harmony even in longer compositions.
The soundtrack will also be made from photos and videos.
Lyria 3 isn't just limited to text. If you upload a photo of a sunset or a travel video, it can create music to match its ambiance. Furthermore, each track can also be accompanied by AI-generated cover art, making content easier to share. Furthermore, Google is also integrating this technology with YouTube Dream Track, where creators can experiment with different music styles for Shorts and other formats.
Watermarking for transparency
To ensure the identity of AI-created content, the company has incorporated SynthID watermarking technology into Lyria 3. This adds an invisible identification to the generated audio, making it clear that it was created by AI.
According to Google, this move is part of its broader strategy towards a multimodal AI platform, where text, images, audio, and video will operate within a single ecosystem. Lyria 3 is currently available in multiple languages for users over the age of 18, while its expansion to the mobile app will occur in a phased manner.
