AI music maker Suno now generates spoken words

AI-generated voiceovers now come with optional synchronized music, changing how content creators can produce audio narratives.

AI music generation company Suno has launched a public beta for a new feature that generates spoken words. The feature, available on its web and mobile platforms, allows users to create voiceovers from scripts or descriptive prompts, and can simultaneously generate background music to accompany the speech. Suno's Chief Product Officer, Jack Brody, stated that the expansion into spoken word aligns with the company's vision beyond just music. This move comes as Suno faces lawsuits related to its music generation tools. The Speech feature offers two modes: a Simple mode for descriptive prompts and an Advanced mode for custom scripts, with options to adjust voice gender, speech style, and voice variety. The maximum duration for generated speech is approximately eight minutes. Suno acknowledges the beta feature has limitations, such as occasional accent drift, and plans to improve it based on user feedback.

Suno's integration of speech generation with music creation marks a significant step toward cohesive, AI-powered audio content production. This unified approach contrasts with existing text-to-speech tools that typically require separate music layering, potentially streamlining workflows for podcasters, audiobook narrators, and video creators. The ability to generate voice and music together as a single track, with adjustable styles and durations up to eight minutes, offers a novel level of creative control and efficiency.

The launch of Suno's Speech feature signals a growing trend in generative AI platforms aiming to offer end-to-end content creation solutions. By incorporating spoken word alongside music, Suno is diversifying its offerings and potentially mitigating risks associated with its music-centric AI. This move will likely spur competition in the AI audio space, pushing other platforms to enhance their capabilities or explore similar integrations to capture a broader market share.