Suno opens a beta of Speech, which it calls the first model to generate voice and music together as one track

Suno, the AI music company, opened a public beta of Speech on 1 October, a tool that makes spoken audio set to original background music. Chief product officer Jack Brody announced it in a post on the company's blog.

Users type in an idea, a poem or their own writing, then describe the voice and the musical style they want. Suno calls Speech “the first audio model that generates voice and music together as one cohesive track”. That is the company's own claim; no outside test is cited.

Suno says it tested Speech with a small group of users for about a month before opening the beta to everyone. The post is frank about the rough edges: it says British accents can drift toward Australian and back, and that “Dramatic pauses may be _very_ dramatic.” The post gives no pricing and no limits on length.

Speech is Suno's first step beyond songs and into spoken audio such as narration and voice-overs, a market where voice-generation companies already sell tools. It came five days before Italy's competition authority opened an unfair-terms case against Suno over its licence terms, announced on 6 October and covered by the Switchboard on 7 October. Details some coverage gives, such as separate modes and clip lengths, are not on Suno's own page and are left out here.

• Confirmed Suno opened the Speech beta to everyone on 1 October, after about a month of testing with a small group of users. Suno
• Claimed Suno calls Speech the first audio model that generates voice and music together as one cohesive track. Suno
• Confirmed Suno's post lists known faults in the beta, including accents that drift and over-long pauses. Suno