Its newest AI music generation model can be customized using your own vocals and tracks.
Its newest AI music generation model can be customized using your own vocals and tracks.
Suno has just unveiled one of its most significant updates with v5.5 of its AI music model. Prior updates primarily focused on enhancing sound quality and producing more lifelike vocals, but v5.5 emphasizes empowering users with greater control. It features three new capabilities: Voices, My Taste, and Custom Models.
According to the release notes, Voices is the feature most requested by users. It enables individuals to train the vocal model using their voice. Users can submit clean acapellas, fully produced tracks with instrumental backgrounds, or simply sing into the microphone on their phone or laptop. The higher the quality of the recording, the less data is needed. To ensure that voices aren’t easily stolen, Suno mandates that users also state a verification phrase. However, this could potentially be circumvented using existing AI models of celebrity voices.
After training the Voices feature, users can have an AI representation of themselves sing over uploaded music or AI-created content.
Furthermore, Custom Models permits users to refine Suno using their personal tracks. Users must upload a minimum of six songs from their collection and assign a name to the custom model. They will then be able to utilize it to influence v5.5’s responses to prompts.
Lastly, My Taste adapts to user preferences and styles over time. It tracks the genres, moods, and artists that users frequently select while generating prompts, and applies this information when the magic wand is in use to automatically create styles.
While My Taste will be accessible to all users, Voices and Custom Models are exclusive to Pro and Premier subscribers.
