AudioLCM
AudioLCM generates high-fidelity audio from text, ideal for developers and researchers in speech synthesis and audio production.
English
English
What is AudioLCM?
AudioLCM is a text-to-audio generation model based on PyTorch that uses latent consistency models to produce high-quality and efficient audio. It is developed by Huadai Liu and others, offering an open-source implementation and pre-trained models. This model can convert text descriptions into realistic audio, making it valuable for applications like speech synthesis and audio production.
