Suno has opened its Speech beta to everyone, expanding beyond AI song generation with a tool for making spoken audio tracks inside the company’s platform.
According to Suno’s Oct. 1 announcement, Speech lets users generate spoken audio set to original background music. The company said the feature is built directly into Suno, so users can type in an idea, poem, or script and then describe the voice and musical style they want.
The Verge reported on Oct. 2 that Speech is available in public beta across Suno’s web and mobile platforms, making the rollout broader than the earlier test group Suno described.
What Suno says Speech does
In its announcement, Suno called Speech “the first audio model that generates voice and music together as one cohesive track,” framing it as a new creative tool alongside its existing music products. The company said it spent about a month testing Speech with a small group before opening the beta more widely.
The core pitch is simple: instead of using a separate text-to-speech app and then adding music somewhere else, Speech is meant to handle both parts in one place. Suno said users can create spoken audio with a matching musical backdrop from a single prompt or piece of writing.
Still very much a beta
Suno also put some limits and caveats front and center. In the company’s words, “beta really does mean beta,” with quirks that can include accents drifting and pauses becoming overly dramatic.
That matters because Suno is presenting Speech as an early version, not a finished product. The company said it plans to keep improving the feature as it learns from what users like, what still does not work well, and how people want to use it.
For users, the practical takeaway is that Speech is now broadly available, but Suno is still treating it as a work in progress rather than a polished final release.
