One script in. A finished narrated track out, with music already sitting under the voice.
That is Suno Speech. The AI music app now reads your words aloud and scores them in the same pass, so you skip the usual routine of recording a voice in one tool, making music in another, and mixing the two files late at night.
What Suno Speech Is
Suno opened Speech as a public beta on October 1, 2026, after a month of testing with a small group. It lives in the Create screen, next to Songs and Sounds, and it is marked Beta. You will find it on web, iOS and Android.
The idea is simple. Speech makes a spoken voice and its original background music together, as one track. Suno calls it the first audio model that does this, and that is the company’s own claim, so treat it as a pitch rather than a proven fact.
Honestly, the one-track part is what makes it fun. A bedtime story does not just get read to you. Soft piano arrives with it.
How to Use Suno Speech
Open Suno and go to the Create screen. Pick Speech. Then choose your mode.
Simple mode is the quick route. You write a one-line description, something like “a pirate captain rallying his crew,” and Speech writes the words and performs them for you.
Advanced mode is for your own script. Paste your text in, and Speech performs it as written, with controls for voice gender, speaking style and how much each take varies from the last one. You also describe the voice and the musical style you want behind it.
Want voice only? Turn the music off with the toggle, and Speech works as a plain text-to-speech tool. Tracks can run to about eight minutes, which covers a short story, a guided meditation or a product demo without much trouble.
Our honest tip: start small. Generate a short piece first, listen to the whole thing, endings included, and only then try a longer script.
What You Can Make With It
Suno’s own examples lean personal, not corporate. Bedtime stories over soft piano. Hype speeches over stadium drums.
You can also try meditations, pep talks, poems and narrated intros for your videos. The release notes even mention ASMR grocery lists, which tells you the team expects weird experiments here.
Where it fits best, we think, is short scored narration. If your clip needs a voice and a mood at the same time, Speech hands you both in one file.
Price, Limits and Honest Beta Notes
There is no separate Speech price. Generations use the same credits as songs, and downloads count against the same monthly caps: 20 downloads a month on Pro and 60 on Premier. A free plan exists, so you can try Speech without paying, but free-plan clips do not carry commercial rights.
Now the rough edges. Suno’s chief product officer Jack Brody wrote that “beta really does mean beta,” and he was not joking. British accents can wander off toward Australia and come back again. Pauses can get very dramatic.
Suno has not published a Speech-specific credit cost per track, a list of supported languages, or separate commercial terms for Speech. So keep early projects personal, listen before you share, and let the beta be a beta.
Short script. One track. Zero mixing.
Sources
- https://openaimaster.com/new-ai-tools-october-2026/
- https://sloptvnews.com/suno-speech-beta-voice-and-music-one-track/
- https://www.unite.ai/suno-launches-speech-beta-pairing-voice-and-music-in-one-model/