Google Unveils Lyria 3 Pro AI Music Model

Google announced on Wednesday the launch of Lyria 3 Pro, a new music generation model, just one month after introducing Lyria 3. This upgraded model enables users to produce tracks up to three minutes in length, a significant increase from the 30-second limit of its predecessor.
The company stated that Lyria 3 Pro not only allows for longer compositions but also provides superior creative control and customization. Users can now specify structural elements like intros, verses, choruses, and bridges within their prompts, as the model has a more advanced understanding of song architecture.
Following the initial integration of music generation into the Gemini app with Lyria 3, the Pro model is also being added to the platform. However, access will be exclusive to paid subscribers. Google is also deploying Lyria 3 Pro within its Google Vids video editing app and ProducerAI, a generative AI-powered music production tool acquired last month.
Furthermore, Google is extending music generation capabilities to its enterprise tools, including Vertex AI (in public preview), the Gemini API, and AI Studio, via the Lyria 3 Pro model.
Google highlighted that the model was trained using data from its partners and permissible sources from YouTube and Google. It clarified that the model does not replicate specific artists. However, if a user references an artist in a prompt, the model draws broad inspiration from that artist's style to generate a track.
All music created with Lyria 3 and Lyria 3 Pro is watermarked with SynthID to transparently indicate AI involvement.
In related industry news, Spotify recently introduced tools for artists to review songs released under their name, aiming to prevent misattribution by AI-generated content creators. Simultaneously, Deezer has launched technology to help streaming services identify AI-generated music.
Related article
Gemini Spark now manages Google Photos library
Google is expanding its AI integration by enabling Gemini Spark to manage Google Photos libraries. Users can now instruct the agent to edit images, organize albums, generate shared collections from favorite shots, convert concert flyers into calendar
Google rolls out fake call detection to protect against AI deepfake impersonation scams
Google announced on Tuesday that Android is launching fake call detection to protect against AI deepfake impersonation scams. The feature is rolling out globally in Phone by Google to Android 12+ devices this month, starting with Pixel devices.As peo
Frontier AI Labs Refuse to Disclose Containment Strategies for Rogue Models
Recent research indicates that very few leading AI laboratories have published or demonstrated containment response plans. A containment plan defines the procedures for when an AI system attempts to subvert human control, specifying which access righ
Related Special Topic Recommendations
Comments (0)
0/500

Google announced on Wednesday the launch of Lyria 3 Pro, a new music generation model, just one month after introducing Lyria 3. This upgraded model enables users to produce tracks up to three minutes in length, a significant increase from the 30-second limit of its predecessor.
The company stated that Lyria 3 Pro not only allows for longer compositions but also provides superior creative control and customization. Users can now specify structural elements like intros, verses, choruses, and bridges within their prompts, as the model has a more advanced understanding of song architecture.
Following the initial integration of music generation into the Gemini app with Lyria 3, the Pro model is also being added to the platform. However, access will be exclusive to paid subscribers. Google is also deploying Lyria 3 Pro within its Google Vids video editing app and ProducerAI, a generative AI-powered music production tool acquired last month.
Furthermore, Google is extending music generation capabilities to its enterprise tools, including Vertex AI (in public preview), the Gemini API, and AI Studio, via the Lyria 3 Pro model.
Google highlighted that the model was trained using data from its partners and permissible sources from YouTube and Google. It clarified that the model does not replicate specific artists. However, if a user references an artist in a prompt, the model draws broad inspiration from that artist's style to generate a track.
All music created with Lyria 3 and Lyria 3 Pro is watermarked with SynthID to transparently indicate AI involvement.
In related industry news, Spotify recently introduced tools for artists to review songs released under their name, aiming to prevent misattribution by AI-generated content creators. Simultaneously, Deezer has launched technology to help streaming services identify AI-generated music.
Gemini Spark now manages Google Photos library
Google is expanding its AI integration by enabling Gemini Spark to manage Google Photos libraries. Users can now instruct the agent to edit images, organize albums, generate shared collections from favorite shots, convert concert flyers into calendar
Google rolls out fake call detection to protect against AI deepfake impersonation scams
Google announced on Tuesday that Android is launching fake call detection to protect against AI deepfake impersonation scams. The feature is rolling out globally in Phone by Google to Android 12+ devices this month, starting with Pixel devices.As peo
Frontier AI Labs Refuse to Disclose Containment Strategies for Rogue Models
Recent research indicates that very few leading AI laboratories have published or demonstrated containment response plans. A containment plan defines the procedures for when an AI system attempts to subvert human control, specifying which access righ





Home






