Suno launches Speech for AI voiceovers with optional music

Suno has launched Speech, a public beta feature that creates AI-generated spoken audio from prompts or custom scripts. The tool can also add background music to the same track. Jess Weatherbed reports for The Verge that Speech is available on Suno’s web platform and mobile apps.

The release expands Suno beyond AI music generation into voice synthesis. Users can choose whether to include music or switch it off for a clean voiceover. Suno positions the combination as useful for formats such as narrated poems, dramatic speeches, and other spoken content that benefits from an accompanying soundtrack.

Two creation modes

Speech offers a Simple mode and an Advanced mode. In Simple mode, users describe the desired result in a prompt. A request might specify a character, mood, or delivery style, such as a pirate captain addressing a crew.

Advanced mode supports a custom script, giving users more direct control over the words spoken. Additional settings allow users to select the voice’s gender, define its speaking style, and adjust the degree of variation between generations. Each generated audio track can run for roughly eight minutes.

Suno chief product officer Jack Brody describes Speech as an audio model that produces voice and music together in one track. The company also stresses that the product remains experimental. Brody says accents may shift unexpectedly, pauses can become overly pronounced, and users may find uses that the company has not anticipated.

The move comes as Suno seeks to broaden its product range. Its AI music generator has faced several lawsuits, while the wider market for synthetic speech already includes established tools from companies such as Adobe and ElevenLabs.