Suno launches Speech function for generating speech with music

The Suno service has released a beta version of the Speech function, which allows generating speech with background music in a single track. The technology combines text input and musical style description to create ready-made audio content.

New tool capabilities

Users can describe an idea or write text, set voice parameters and musical genre. The system independently generates smart narration text and an original backing track, creating a single audio file without the need for separate mixing.

The tool is suitable for the following tasks:

• Video and story narration
• Creating advertising commercials
• Recording podcast inserts
• Generating meditative content
• Narrating game scenes

Platform strategic development

Suno is transforming from a music generator into a tool for creating comprehensive audio content. The key difference from traditional speech synthesis (TTS) systems lies in simultaneously creating voice and soundtrack as a unified scene.

The feature is available to all Suno users for free as part of the beta test. There is no separate tariff for Speech, although the exact amount of credits consumed is not yet specified. If necessary, you can try disabling the musical backing.

More about the launch:

Official announcement and technical details are available on the developer's website.