AI music generator Suno can now create spoken audio with matching background music
Suno, an AI music generator, is introducing a feature called Speech that generates spoken text and matching background music as a single audio track. Users input an idea or written text and specify the desired voice and music style, and the model generates both the voice and the sound.
According to Suno product chief Jack Brody, the company tested Speech with a small group for a month. Suno says the feature is intended for use cases such as poems, meditations, and bedtime stories. The beta still has bugs, including that a British accent can sometimes sound Australian.
Suno has not disclosed how it trained the model. The announcement comes as AI music generators face criticism over potential copyright infringement. Major record labels have already sued Suno, and a Munich court recently ruled against the startup, rejecting fair use as a justification for using copyrighted data.
Based on reporting from the original publisher. Visit the source for full context and later updates.
Publisher excerpt
Suno is adding a feature called "Speech" to its AI music generator that creates spoken text with matching background music in a single audio track. The company says it's built for things like poems, meditations, and bedtime stories. Suno hasn't said how the model was trained. The article AI music generator Suno can now create spoken audio with matching background music appeared first on The Decoder .