Suno Unleashes AI Speech Generation

Suno, known for its AI music generation, has introduced a new Speech feature now available in public beta. This expansion allows users to generate spoken voices based on scripts or descriptive prompts. The feature is designed to create voiceovers that can be accompanied by AI-generated background music, blending these elements into a single audio track.

Users can utilize either a Simple mode for prompt-based descriptions or an Advanced mode for custom scripts, including options to select voice gender and speech style. This new capability aims to diversify Suno's offerings, potentially addressing concerns stemming from previous lawsuits related to its music generation. The maximum duration for generated speech is approximately eight minutes.

Suno acknowledges that the Speech feature is currently in beta and will be improved based on user feedback. They anticipate occasional unique quirks, such as accent variations or dramatic pauses, and encourage users to explore its diverse applications. This move signifies Suno's broader ambition to encompass various forms of human expression beyond music.