Suno opens Speech voice-and-music generator to public beta

Suno opened Speech to everyone in beta on October 1. The launch expands its generative-audio platform with a tool the company says can produce spoken voice and original background music together from written input.

According to the company’s release notes, the beta is available on Suno’s web and mobile products. Suno said the public opening followed a month of testing with a small group of users.

Users can enter an idea, poem or other text, then describe the voice and musical style they want, according to Suno. The company describes Speech as its first audio model designed to generate voice and music as one cohesive track.

Speech extends Suno beyond the music-generation focus of Suno’s v6 music-model rollout. The company did not disclose Speech-specific pricing, usage limits, model architecture or training data in the sources reviewed.

Suno stressed that Speech remains unfinished beta software. It identified accent drift and overlong dramatic pauses as current flaws and said it plans to improve the product using feedback from the wider community.