Suno Launches Speech Beta, Generating Voice and Music in One Model

Suno opened its Speech beta on October 1, 2026, a spoken-audio model the company says is the first to generate voice and music together as a single track. The beta is available to all users on mobile and web, letting them type text and describe the voice and musical style they want.

• Speech beta is open to all users on Android, iOS and web as of October 1, 2026
• The model generates speech and its background music in one take rather than separately
• Suno warns of beta quirks, such as a British accent drifting into Australian
• The launch follows the v6 music models released September 9, 2026 with Warner, BMG and Believe