Suno announced Speech (beta) on October 1, 2026. Suno describes it as “the first audio model that generates voice and music together as one cohesive track.”
What to know
- How it works: you enter an idea, a poem or your own writing, then describe the voice and the musical style you want. The result is spoken audio set to original background music.
- Availability: Suno says it tested Speech with a small group for about a month and is now opening the beta to everyone. The post does not say which plans include it or what it costs.
- Beta limits: Suno says “beta really does mean beta”. It notes that British accents can occasionally drift into Australian and that dramatic pauses may be very dramatic.
- Voices and rights: the post does not explain voice cloning, consent or rights. Check Suno’s current terms before publishing anything commercially.
Why it matters
Until now, a spoken-word piece with a music bed meant generating the voice and the music separately and mixing them. If you want to try the new format, start with our guide to writing AI music prompts and describe the voice as carefully as the genre. See also Suno, Suno v6 and the model tracker.
Source: Suno blog. We summarise in our own words; check the source for the full details.