Model training and deployment

Audio-SDS is a framework that applies Score Distillation Sampling (SDS) concepts to audio diffusion models. The technology enables leveraging large pre-trained models for a variety of audio tasks, such as physically guided impact sound synthesis and cue-based source separation, without the need for specialized datasets. Its main advantage is that through a series of iterative optimizations, complex audio generation tasks become more efficient. This technology has broad application prospects and can provide a solid foundation for future audio generation and processing research.

Kimi-Audio is an advanced open source audio base model designed to handle a variety of audio processing tasks such as speech recognition and audio dialogue. The model is massively pre-trained on more than 13 million hours of diverse audio and text data, with powerful audio inference and language understanding capabilities. Its main advantages include excellent performance and flexibility, making it suitable for researchers and developers to conduct audio-related research and development.

Audiobox is Meta's next-generation audio generation research model that leverages voice input and natural language text prompts to generate sounds and sound effects, making it easy to create custom audio for a variety of use cases. The Audiobox series of models also includes professional models Audiobox Speech and Audiobox Sound. All Audiobox models are built on the shared self-supervised model Audiobox SSL.