Skip to content

WAND-Sonic โ€‹

Updated

Handles audio AI processing. It automates sound-related work through source separation and multilingual AI dubbing.

Main Features โ€‹

  • Audio Separation: Separates vocals, accompaniment, and sound effects from video track by track
  • AI Dubbing: Clones the original voice to generate multilingual dubbing

Getting Started โ€‹

Voice processing results are output as audio files such as MP3 and WAV.

API authentication is required. From the TokenHub document in Quick Start, issue the API key.

Built with VitePress ยท Deployed on Tencent EdgeOne Pages