AI music tool Suno now offers voice generation in public beta

Suno, an AI music platform, has introduced a new feature called Speech that generates spoken voices. Available in public beta across Suno's web and mobile platforms, users can now create voiceovers embedded with AI-generated background music. This feature aims to offer a cohesive audio experience by combining text-to-speech technology with music generation.

In practice, this means developers and product teams can experiment with creating voice and music tracks for apps or marketing content. However, since this is still a public beta, there might be limitations in performance or accessibility. Suno's offering is unique as it allows users to generate music and speech together or independently, depending on the need.

AI-generated speech technology is not new. Companies like Adobe and ElevenLabs have been in this area for a while. Suno's approach of integrating it with music is distinct, potentially offering smooth transitions between spoken word and music without manual editing. Users can select or disable the background music feature, providing flexibility for different use cases like soothing tracks for storytelling or energetic soundtracks for promotional videos.

Source: AI | The Verge