项目描述
Step-Audio is an open-source framework for intelligent speech interaction, supporting multilingual conversations, emotional tones, regional dialects, adjustable speech rates, and prosodic styles. It features a 130B-parameter multimodal model for speech recognition, semantic understanding, dialogue, voice cloning, and speech synthesis.
项目信息
创建于 2/11/2025
更新于 7/2/2025
分类
speech-technology
conversational-assistant
ai-content-generation
标签
open-source-community
multimodal
model-deployment
development-tools
ready-to-use