Suno opened its Speech beta to everyone on October 1 after a month of testing with a smaller user group. The feature generates spoken audio with original background music as a cohesive track.
Users enter an idea, poem or other text and describe the voice and musical style they want. Speech is built into Suno rather than presented as a separate editing application.
Creative uses and beta limits
The company describes potential uses such as dramatic readings, meditations, pep talks and bedtime stories. Those examples illustrate the intended creative scope; they are not guarantees about the quality of a particular output.
Suno cautions that the beta can produce inconsistent accents and exaggerated pauses. Its launch announcement does not detail Speech-specific pricing or commercial-use rights, so those terms should be checked separately before using generated audio in a paid project.
Source
Feature image: AI-generated editorial illustration for Guava Insights. Conceptual artwork, not a product photograph or depiction of an actual facility or legal proceeding.
