Suno Adds AI Speech Generation to Its Music Platform

AI music platform Suno launched a speech generation feature in public beta in October 2026, allowing users to create AI-voiced audio from written scripts or text prompts, with optional background music included.

The feature, called Speech, is available on Suno’s web and mobile platforms. Users can choose between two modes: Simple, which generates voice audio from a descriptive prompt such as “a pirate captain rallying his crew,” and Advanced, which accepts a custom script and offers additional controls over voice gender, speech style, and generation variety. Outputs can run up to approximately eight minutes.

A key element of Suno’s approach is the simultaneous generation of voice and music as a single track. Background music can be toggled off for clean speech output, but the combined format is designed to suit use cases such as narrated poems or dramatic voiceovers. Jack Brody, Suno’s chief product officer, described it as “the first audio model that generates voice and music together as one cohesive track.”

Suno acknowledged the feature has limitations at launch. “Beta really does mean beta,” Brody said. “Occasionally, British accents can wander off to Australia and back. Dramatic pauses may be very dramatic.”

The company enters a field that already includes established players. The source notes that DeepMind has worked on deep learning speech synthesis for a decade, Adobe offers a text-to-speech tool, and ElevenLabs has operated as a recognized platform in the space since 2023. The source also notes that Suno’s core music generator has attracted multiple lawsuits, suggesting the expansion may reflect an effort to diversify the platform’s offerings.

Suno said it plans to continue refining Speech based on user feedback.