Google has introduced a new AI music generation model dubbed as Lyria 3 Pro. The new model allows users to create longer and more detailed music tracks using simple prompts. With this release, Google is also expanding access to AI-powered music generation across several of its platforms. According to the tech giant, Lyria 3 Pro can generate music tracks that are up to three minutes long.
Also, the new model is said to have a better understanding of musical composition. So, users can prompt for specific elements like intros, verses, choruses and bridges. The company says it is ‘great for experimenting with different styles or generating songs with complex transitions.’
Google also emphasises that all music generated by Lyria models is marked with SynthID, a watermark that identifies AI-generated content.
Also read: OpenAI is killing Sora AI video generation app, leaves internet divided
Google is rolling out Lyria 3 Pro AI music generation model across several of its tools and platforms.
The model is available in Vertex AI in public preview. Organisations can use it to generate audio content at scale. Developers can access the model through Google AI Studio and the Gemini API. Another place where the model is available is Google Vids, the company’s AI-powered video creation tool. This will allow users to generate custom music to match their videos.
Also read: Apple testing standalone Siri AI app to compete with ChatGPT, Gemini: What it may offer
Lyria 3 Pro is also being added to the Gemini app, starting with paid subscribers. In addition, Google has integrated the model into ProducerAI, a collaborative music creation tool. ‘To protect original expression, Lyria 3 and Gemini do not mimic artists; if a prompt names a creator, the model takes that as broad inspiration,’ the tech giant explains.
Also read: Anthropic’s Claude AI can now use your computer to complete tasks, but there’s a catch