Suno opens its Speech beta to everyone, generating a voice and background music as one track

Suno is known for generating songs from a text description. Speech adds spoken word to the same app. The announcement is signed by Jack Brody, the company's chief product officer. It says Suno tested the feature with a small group of users for a month before opening the beta to everyone.

What Speech does

You type an idea, a poem, or a text you have written, then describe the voice and the musical style you want. Speech returns spoken audio with original background music. Suno describes it as the first audio model that generates voice and music together as one cohesive track. That claim is the company's own.

The announcement lists the uses Suno found during testing: meditations, poems, pep talks, bedtime stories, and dramatic readings of friends' text messages.

How you reach it, according to The Verge

The Verge reports that Speech is available in Suno's web and mobile apps, under the Speech option in the Create tab. Its report describes two modes. Simple mode takes a description of what you want. Advanced mode accepts your own script and adds settings for the voice. The Verge also reports that the background music is optional and can be switched off. Suno's announcement does not describe these controls.

What the beta label covers

Suno says the beta label is meant literally. The announcement warns that an accent can change partway through a recording, for example from British to Australian, and that pauses can run long. The company says it will keep improving Speech based on what users make with it.

What is not confirmed yet

The announcement does not say how many credits a Speech generation costs, or whether the feature differs between the free and paid plans. It also gives no maximum length and no list of supported languages. Suno's pricing page lists credits per plan and does not mention Speech. That was the state of the page when it was checked on October 2, 2026.