Suno Music AI Releases Version 5.5 with Focus on User Vocals

The developers of Suno AI have announced the release of version 5.5, calling it the “highest quality and most expressive” version to date. The key new feature is the ability to accurately replicate a user’s own voice—a move aimed at capturing the attention of the professional music industry.

Subscribers to the Pro and Premier plans now have access to a feature that allows them to record their voice or upload an existing audio file. The neural network analyzes the timbre and combines it with a prompt to generate new songs with any lyrics. The length of the uploaded audio sample must be between 30 seconds and 4 minutes.

Developers have implemented safeguards against using someone else’s voice: to activate the feature, users must pass a real-time verification by reading a text displayed on the screen. The system records the voice signature and links it to the account.

The platform accepts both clean a cappella recordings and files that already contain background music. The creators emphasize that the neural network does not require professional studio equipment.

Among other improvements is the option to train the model on a user’s own music, ensuring that all future generated tracks closely match their signature style. Additionally, the algorithm becomes more precise in identifying user preferences as the number of created tracks increases