Skip to content
by InfinyAI ES

IA en un minutoNewsTools

ToolsUpdated:

Suno adds voice generation to its AI music platform

IA en un minuto newsroom · Editor: Jon Elgezabal

In 30 seconds

Speech is Suno's new model: from a text plus a description of the voice and music, it produces narration with original background music as a single track. According to the company, it has been used for meditations, bedtime stories and pep talks, and after a month of testing with a small group the beta is now open to everyone. Suno admits it still stumbles with some accents and pauses, and it gives no prices or languages.

On October 1, Suno, the platform that creates songs with artificial intelligence, introduced Speech, a model that generates spoken audio over original background music. Suno describes it as the first audio model to produce voice and music together, as a single track.

It works inside Suno: users write an idea, a poem or a text of their own and describe the voice and the musical style they want. The company says that during development its team used it for bedtime stories, meditations, pep talks and poems, and also to turn friends' messages into dramatic readings or to give everyday voice notes an epic score.

The announcement is signed by Jack Brody, chief product officer, who presents Speech as a natural extension of what people already do on Suno, where songs are made every day for birthdays, weddings or inside jokes. Music, he adds, will remain at the heart of the platform.

Speech is in beta. Suno spent the past month trying it out with a small group of users and is now opening the beta to everyone. The company itself warns that it still slips up: Brody wrote that British accents can occasionally "wander off to Australia and back," and that dramatic pauses may be very dramatic. It will keep improving the model based on what works and what its community asks for.

The announcement does not include pricing or say which languages Speech supports.

Why it matters · analysis and opinion

Voice and music now come out on the same track, without a studio or mixing, and that changes who can make a voice-over. Until now it meant recording, finding licensed music and putting it all together; with Speech you just write the text and describe the tone. The winners are those producing audio on a small budget: a podcast, a shop that wants a welcome message, a social media account. Voice artists and studios that live off short pieces have more to lose. But it is a beta with flaws Suno itself acknowledges, such as accents that wander off and come back mid-sentence, and the announcement does not say which languages it supports or what it costs. For now it works for mock-ups; for an ad that will go on air, listen to all of it and check what the plan allows for commercial use.

Official source: Suno · Written with the help of AI: how we make the news

AI in your inbox, every day or every Friday

The stories that matter, each one in a minute. With the source for every one.

Choose one or both:

Sign up and you are in: the daily arrives every night and the weekly on Friday mornings. You can unsubscribe from any email.