Audiobox is a free and open source AI voice and sound generation model launched by Meta on November 30, 2023. It will be launched on December 11, and users can experience the capabilities of the model for free. Audiobox is Meta’s latest generation audio generation model after Voicebox, which can use voice input and natural language text prompts to generate voice and sound effects, making it easy to create realistic custom audio for a variety of use cases.
Audiobox’s main features
- Clone user voice: Record sounds to generate voice in the user’s voice style or in the style of any audio sample
- Generate vocals by text description: Use text to describe the characteristics of sound style and to generate vocals by acoustic environment
- Change sound style: You can change existing sound styles by combining sound and text descriptions
- This article describes the generation of sound effects: generate sound effects based on the input sound characteristics text description
- Noise cancellation: Provides Magic Eraser function to eliminate transient noise in recordings
- Sound filling: Replace part of the audio with a new sound according to the text description
- Audio Story Maker: Use Audiobox Maker to create original and interesting audio stories