Suno's Speech beta generates voice and music together

Suno released Speech into open beta, described by the company as “the first audio model that generates voice and music together as one cohesive track.” Rather than generating spoken audio and then backing it with music, the model produces both at once, so the delivery and the arrangement are designed together rather than layered.

It lives inside Suno alongside the existing v6 model line and Suno Studio. You type an idea, a poem or written text, then describe the voice and the musical style you want. Suno tested it with a small group of users over the past month and the beta is now open to everyone.

What is missing from the announcement is as notable as what is in it. There is no pricing, no duration cap, no plan tier, no model name and no stated capability limits. None of that is published on the page.

The honest framing from Suno’s own chief product officer is that beta means beta. The stated quirks are that British accents can wander to Australia and back, and that dramatic pauses may be very dramatic. The word “rough edges” appears as well.

(Original source: Suno)