Suno launches Speech, a voice generation feature, in public beta
Understand the story
On October 2, 2026, The Verge reported that Suno launched a speech generation feature called Speech, opening a public beta on web and mobile. The feature can generate both voiceover and background music from a script or prompt. Speech offers two modes: Simple and Advanced. Simple mode is easy to use, while Advanced mode supports custom scripts and allows adjusting the AI voice's gender, speech style, and degree of variation. Generated audio is capped at about eight minutes. Users can turn off background music via a toggle, keeping only the voice. The company acknowledged the feature is still imperfect and said it will continue improving based on user feedback.
AI overview of reporting · Updated 16 days ago
Reporting timeline
Explore different aspects of the story through its reporting.
- The Verge · AIAI music maker Suno now generates spoken words
Suno launched its Speech feature in public beta on web and mobile, generating voiceovers and background music simultaneously from a script or prompt. The feature offers Simple and Advanced modes, with Advanced supporting custom scripts and adjustments to the AI voice's gender, style, and variation, with a duration cap of about eight minutes. Background music can be toggled off, and the company acknowledges the feature is still imperfect and will keep improving it based on user feedback.