Suno Launches Speech Beta

Suno has opened its Speech beta to all users, allowing the creation of spoken audio set to original background music. This feature combines voice and music generation, marking it as the first audio model of its kind from Suno. The beta testing phase lasted one month and involved a small group of users.

Suno claims that while the model performs well, it has noted occasional issues with British accents, which can sometimes shift to Australian pronunciations. The company aims to refine the Speech model based on user feedback, stating, "We’ll keep improving Speech as we learn what people love, what doesn’t quite work yet, and what our community wants to do next."

This launch follows a trend in AI audio models, as seen in recent developments like DoorDash's text-to-order AI agent. Practitioners in audio and music technology can leverage this new capability to enhance content creation processes, particularly in areas requiring synchronized voice and music integration.