AUTO-UPDATED

AI music maker Suno now generates spoken words

AI music platform Suno has launched a public beta for its new Speech feature, allowing users to generate synthetic voiceovers alongside custom background music tracks on its platform.

Key Points

  • The Speech feature is now available on Suno’s web and mobile platforms for creating voiceovers up to eight minutes long.
  • Users can choose between a Simple mode for prompted descriptions or an Advanced mode for custom scripts with adjustable voice settings.
  • The tool allows for the simultaneous generation of spoken word and background music, though the music can be toggled off for clean audio.
  • Suno’s expansion into text-to-speech competes with established providers like ElevenLabs and Adobe.
  • The company acknowledges the feature is in early beta and expects performance inconsistencies as it gathers user feedback.

Why it Matters

This expansion allows Suno to diversify its generative audio offerings beyond music, potentially mitigating risks associated with its primary music-focused business model. By integrating voice and music into a single workflow, the company aims to capture a broader market of content creators seeking cohesive, all-in-one audio production tools.
The Verge Published by Jess Weatherbed
Read original