Suno Introduces Speech Feature That Adds Voice and Background Music to Text

“Suno” has released its new “Speech” feature in open beta on its web and mobile apps. The tool generates synthetic speech based on a written script or a short description. Users can also simultaneously create AI-generated background music to match the voice. According to the company, this is the first model to combine voice and music in a single audio recording.

To create audio, users need to select the “Speech” feature from the “Create” section. The tool has 2 operating modes. In “Simple” mode, it is enough to briefly describe the scene. For example, a user can create a speech by a ship captain motivating the crew. In “Advanced” mode, a prewritten script can be added to the system.

In “Advanced” mode, users can select the gender and speaking style of the synthetic voice, as well as adjust how different each result will be. Background music is optional and can be turned off with a button. “Suno” presents calm poems, dramatic narrations, and motivational speeches as examples. The maximum duration for a single audio recording is approximately 8 minutes.

According to “Suno,” “Speech” is not yet fully ready. Beta testing will continue based on user feedback. Jack Brody said the system may sometimes switch from a British accent to an Australian accent. Dramatic pauses can also sometimes be considerably longer than expected. The company expects users to find new ways to use the tool in addition to encountering these issues.