Audiobox

Audiobox is a free and open-source AI voice and sound generation model launched by Meta on November 30, 2023. The online web version was launched on December 11, and users can experience the model’s capabilities for free. Audiobox is the latest generation of audio generation model launched by Meta after Voicebox. It can combine voice input and natural language text prompts to generate speech and sound effects, making it easy to create realistic custom audio for various use cases.
The main functions of Audiobox
Clone user voice: Record voice to generate voice based on the user’s voice style or any audio sample style
Text description for generating vocals: Using text to describe the characteristics of sound style and acoustic environment for generating vocals
Change Sound Style: Existing sound styles can be changed by combining sound and text descriptions
This article describes generating sound effects: generating sound effects based on the text description of input sound characteristics
Noise cancellation: Provides Magic Eraser function to eliminate transient noise in recording
Sound filling: Replace a part of the audio with a new sound based on the text description
Audio Story Maker: Combining the above functions, use Audiobox Maker to create original and interesting audio stories