Suno adds Speech, a voice and background music generator
Speech is in public beta on Suno's web and mobile apps and makes a voiceover and matching music as one track.
Suno, best known as an AI music generator, has launched Speech, a feature that produces spoken text and matching background music together as a single audio track. It is in public beta across Suno's web and mobile platforms. You type an idea or a script, describe the voice and music style you want, and the model generates both.
How Speech works
You find it under the Create tab, in the Speech option. Simple mode takes a description, such as "a pirate captain rallying his crew". Advanced mode lets you add your own script and adjust the gender of the voice, the speech style and how much variety each generation has. The background music is optional, so you can switch it off with a toggle if you only want clean speech. Speech has a maximum duration of around eight minutes.
Suno suggests uses such as poems, meditations and bedtime stories, with a calm soundtrack for some and something more energetic for dramatic voiceovers. Suno tested the feature with a small group for a month before this release.
Still a beta
Suno's chief product officer, Jack Brody, says the beta has bugs. "Beta really does mean beta," he said, adding that British accents can wander off to Australia and back and dramatic pauses may be very dramatic. Suno says it will keep improving Speech based on user feedback.
Training data and legal questions
Suno has not said how it trained the Speech model. That matters because AI music generators face criticism over possible copyright infringement. Major record labels have already sued Suno, and a Munich court recently ruled against the company, rejecting fair use as a justification for using copyrighted data. If you plan to use the audio commercially, keep those open questions in mind.
Where it fits
AI speech is not new. Adobe has a text-to-speech tool and ElevenLabs has been one of the best known platforms since launching in 2023. Suno's difference is generating the voice and the music together in one pass. The Verge suggests the move is likely an attempt to diversify the platform, given the lawsuits over its music generator.