Published: 10/2/2026
Source: The Verge — Suno Speech Beta
Suno has expanded beyond song generation with Speech, a public beta that creates spoken voice tracks from descriptions or complete scripts and can generate accompanying background music in the same output.
Speech is available on Suno’s web and mobile apps. Simple mode accepts a descriptive prompt, while Advanced mode accepts a custom script and provides controls for voice gender, speaking style and variation.
Outputs can run for approximately eight minutes, and users can turn off the generated music when they need clean speech. Suno warns that the beta may produce inconsistent accents and exaggerated pauses.
Why it matters: Suno creators can now prototype narration, poetry, dramatic monologues, podcast segments and spoken-word music without moving between separate voice and music generators. Commercial users should still verify Suno’s applicable terms and independently review every output for accuracy and rights concerns.