AI music generator Suno can now create spoken audio with matching background music
decoder ·
Suno, an AI music generator, has introduced a new feature called Speech that combines spoken text with matching background music into a single audio track. Users can input written ideas or text and specify desired voice and musical styles to generate the final product. Product chief Jack Brody confirmed that the company tested this capability with a small group for one month prior to release. The feature is intended for creative applications such as poems, meditations, and bedtime stories, although the beta version currently contains bugs like inconsistent accents. This development occurs amid significant legal challenges for Suno, including lawsuits from major record labels alleging copyright infringement. A recent ruling by a Munich court rejected the startup's fair use defense regarding the use of copyrighted data in training its models. Suno has not disclosed how it trained the underlying model for this new speech functionality.
decoder