Suno opens Speech beta for spoken audio generated together with original music

On October 1, 2026, Suno opened a public beta of Speech, which creates spoken audio set to original background music. Suno calls it the first audio model that generates voice and music together as one cohesive track.

Archive entry: this covers an event from October 1, 2026, and we published it on November 8, 2026. The details come from sources dated at the time and may have changed since.

On October 1, 2026, Suno opened the beta of Speech, which creates spoken audio set to original background music, to everyone. Jack Brody, Suno's Chief Product Officer, announced it in a post on the Suno blog.

What Suno released

Suno called Speech the first audio model that generates voice and music together as one cohesive track.
Speech was integrated into Suno: the user typed an idea, a poem or their own writing, then described the voice and the musical style.
Example uses named in the post included meditations, verse, pep talks and bedtime stories.
Suno tested Speech with a small group of users for about a month before opening the beta to everyone.

What it means for people who build with AI

Creators could make narrated pieces such as meditations or story audio with music in a single generation, instead of mixing separate speech and music tracks. A short idea, a poem or a creator's own writing could be the starting point, with the voice and the musical style described in words.

Beta status and details not stated

Suno cautioned that beta really does mean beta, giving the example that British accents can wander off to Australia and back. The post listed no plan restrictions, pricing, languages or usage limits, so those details were not stated at launch.

Sources

Introducing Speech (beta) (Suno, October 1, 2026, official)

Written with AI assistance, strictly from the sources listed above. Before it went live, automated checks verified its dates, sources and every language edition.