Suno opens Speech beta for voice over generated music

Suno announced Speech beta on October 1. It describes the model as creating voice and music together in one track. Users can enter an idea, poem, or other writing, describe the voice and musical style, and generate speech over original background music. Suno says the beta is open on mobile and web after testing with a smaller group.

This combines two media layers instead of asking creators to edit them by hand. It could shorten the path from a script or voice note to a narrated clip, lesson, meditation, or internal update. The trade-off is that timing, pronunciation, and musical emphasis become coupled in one generation step.

Test one repeatable format with a fixed script and a few voice directions. Score clarity, timing, music balance, and editability. Keep a separate export or fallback recording path until the beta handles names, pauses, and revisions consistently.