Suno, best known for its AI music generator, is branching into spoken audio. The company has launched Speech, a public beta feature that creates synthetic voiceovers from a text script or a descriptive prompt. According to The Verge, Speech can produce voice and background music together as a single track, though users can toggle the music off for clean speech.
The feature offers two modes: Simple, where users describe what they want, and Advanced, which accepts a custom script and includes controls for voice gender, speech style, and output variety. Suno positions this as a natural extension of its mission, with chief product officer Jack Brody saying the company's vision extends beyond music to other forms of human expression.
Suno enters a crowded field of AI voice tools, including ElevenLabs and Adobe's text-to-speech offerings. The move may also help the company diversify its business, as its music generator has attracted multiple lawsuits. Suno acknowledges the beta has rough edges, with Brody noting that accents may wander and dramatic pauses may be very dramatic, but says it will keep improving the feature based on user feedback.