Suno expands beyond music with AI-generated speech and voiceover feature

Suno, known primarily for generating songs with artificial intelligence, is broadening its capabilities by introducing a speech synthesis tool. The feature, now available in public beta on both web and mobile, lets users create AI voiceovers while simultaneously generating accompanying background music as a single cohesive track.

How the speech feature works#

Users can access the Speech tool through the "Create" tab and choose between two modes. The Simple option lets creators describe what they want with text prompts — such as "a pirate captain rallying his crew" — and the system generates appropriate speech and music. Advanced mode allows users to input custom scripts directly, giving more precise control over the dialogue. Additional settings enable adjustments to voice gender, speech style, and the variation level between generations. Tracks can be up to approximately eight minutes long, and the background music can be toggled off if clean speech alone is preferred.

Part of a diversification strategy#

While AI-generated speech itself isn't novel — DeepMind has explored deep learning speech synthesis for over a decade, and platforms like Adobe and ElevenLabs offer their own versions — Suno's pairing of voice with music represents a distinct approach. The move appears designed to diversify the platform, which has faced mounting legal challenges tied to its music generation capabilities, including multiple copyright lawsuits.

What to expect in beta#

Suno acknowledges the feature remains a work in progress. Spokesperson Jack Brody noted that the company intends to refine the tool based on user experience, stating that "beta really does mean beta." Early limitations include unpredictable accent shifts and occasional exaggerated pauses, though the company expects users to discover novel applications beyond its original vision.

The simultaneous generation of voice and music opens possibilities for creators seeking complementary audio — calming soundtracks for poetry readings or energetic accompaniment for dramatic speeches, for instance.