Suno, a company primarily known for its AI-generated music, has introduced a new feature that allows users to generate spoken-word audio. This functionality enables the creation of synthetic voices based on text scripts or descriptive prompts. The feature is currently available in public beta across Suno’s web and mobile applications. A distinct component of this update is the ability to generate a voiceover alongside background music in a single process, streamlining the creation of narrated audio content.
Expanding Beyond Music Synthesis
This development, as reported by The Verge, marks a significant shift for Suno as it moves into the broader synthetic audio market. Until now, the platform focused on melodic and rhythmic generation, typically including sung vocals. By adding spoken word capabilities, Suno is entering a competitive landscape currently occupied by text-to-speech specialists and voice cloning services. The integration of background music with narration suggests the platform is positioning itself as a more comprehensive tool for creators who need to produce podcasts, advertisements, or short-form social media content without using separate editing software.
Missing Details and Future Considerations
While the feature is now live for beta testing, several technical specifications have not been disclosed. The announcement did not specify the total number of unique voices available to users or whether the platform supports multiple languages beyond English. It is also unknown if users have the ability to clone their own voices or if they are restricted to a preset library of synthetic narrators. Furthermore, Suno has not provided information regarding the maximum character count for scripts or how the feature will be priced once the beta period concludes. Observers will also be looking for details on the safety measures in place to prevent the misuse of the speech generation tool for creating unauthorized deepfakes.
As Suno transitions from a music-only service to a multi-purpose audio platform, the success of this beta will likely depend on the naturalness of the speech and the ease of its background music integration.
Lead image: Zhengyang TIAN / Pexels
