Suno, best known for its music-generation tools, announced the public beta of Speech on October 1, 2026. According to the company, the feature creates spoken audio with an original background score, based on the text or idea the user provides and a description of the desired voice and musical style.
In its launch announcement, the company explains that the beta follows a trial with a small group of users. Its release notes say the feature is available on the web and mobile.
Giving original writing a voice and a soundtrack
For writers and content creators, this approach may be useful when they already have a short piece of writing and want to hear it with musical accompaniment. Possible examples include an original podcast introduction, a story passage of your own, or opening remarks for an event. These are ideas for possible uses, not results we tested with the tool.
The combination also raises a creative question: should the words or the atmosphere lead the piece? In an explanatory passage, prominent music can compete with the message. In a story, a long pause can reinforce a moment or interrupt it. That makes listening to the entire result more important than judging it on the opening line alone.
It is still a beta
Suno itself notes that accents may change during a clip and that pauses in the speech may be exaggerated. Keep those limitations in mind when considering uses that require consistent narration.
As of October 3, 2026, the sources we checked did not specifically confirm which languages Speech supports, its availability by country, its pricing, or commercial usage rights for its output. The announcement is therefore chiefly interesting as a new direction for audio creation; it does not yet provide a basis for recommending a paid plan or using the output in a commercial campaign.
Why Suno is moving into speech
Suno describes Speech as the first audio model that generates voice and music together as one cohesive track. It says music will always be at the heart of the product, but that its vision has always extended to other forms of expression. It calls this direction “creative entertainment” and says it will define the next wave of consumer technology.
Speech is built into Suno itself. In its blog post, the company lists uses it found while developing it: dramatic readings of friends’ texts, epic scores for ordinary voice notes, meditations, poems, pep talks and bedtime stories. Its release notes add examples such as bedtime stories over soft piano and hype speeches over stadium drums. The small-group test ran for about a month, and the beta is now open to everyone.
What it means for you
- Availability: Suno says the beta is open to everyone, on the web and mobile. The announcement does not mention any country restrictions in the US, EU or UK, and it does not confirm them either.
- Languages and accents: Suno has not published a list of supported languages or accents, and it warns that accents can drift mid-clip. Listen to every result in full.
- Before commercial use: the announcement gives no pricing or usage rights. Check your plan’s terms before using output in an ad or a client video.
- Related tools: if you pair narration and music with video, see all our hands-on tests in our AI video tools guide.
Sources
- Suno blog: Introducing Speech Beta
- Suno: release notes
