Suno has introduced a new feature enabling the generation of spoken voices alongside music, expanding its capabilities beyond music composition. The Speech feature is now available in public beta across the company’s web and mobile applications. Users can generate voiceovers from scripts or descriptive prompts, with the option to include complementary background music or disable it entirely depending on their needs.
The feature operates in two modes: Simple mode allows users to describe their desired output through a prompt interface, while Advanced mode accommodates custom scripts and provides granular controls over voice characteristics including gender, speech style, and vocal variety. The maximum duration for generated speech is approximately eight minutes. Suno positions this as a tool suited for various applications, such as adding atmospheric soundtracks to poetry or pairing energetic compositions with dramatic narration.
According to Suno Chief Product Officer Jack Brody, the expansion reflects the company’s broader vision beyond music creation. While acknowledging that AI-generated speech technology is established—with competitors including DeepMind, Adobe, and ElevenLabs—Suno is integrating voice and music generation as a unified offering. This diversification effort comes as the music generator has faced multiple lawsuits.
The company has acknowledged current limitations in the beta release, with known issues including accent inconsistencies and irregular dramatic pauses. Brody stated the team plans to refine the feature based on user feedback and anticipates discovering unforeseen applications through public testing.
Article Attribution | Read More at Article Source
Article summary produced by Claude AI