AI music generator Suno has expanded its capabilities with the launch of its new "Speech" feature, currently in public beta on its web and mobile platforms. The feature allows users to generate synthetic voiceovers that are integrated with AI-generated background music into a single audio track.
Suno launches Speech beta, integrating AI-generated voices with background music
According to Suno Chief Product Officer Jack Brody, the goal of the expansion is to extend the platform's vision of human expression beyond music. The new feature provides two modes for creation: a "Simple" mode, where users can describe the desired output via a prompt, and an "Advanced" mode, which allows for custom scripts and adjustments to voice gender, speech style, and variety.
The generated audio has a maximum duration of approximately eight minutes. Users also have the option to toggle off the background music to produce speech-only tracks. Suno noted that the feature is still in the beta stage and will be improved based on user feedback.
Sources
- AI music maker Suno now generates spoken words （The Verge AI, 2026-10-02）