QwenAudio
QwenAudio's tracked open-source repos, sorted by stars.
- #1
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
★ 23,426+498Star change over the last 7 days - #2
Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.
★ 9,209+53Star change over the last 7 days - #3
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents
★ 2,356+54Star change over the last 7 days - #4
Open-source LLM-based ASR model family for Chinese, dialect, accent, and multilingual speech, with FunASR, vLLM, streaming, and llama.cpp runtimes.
★ 1,512+14Star change over the last 7 days - #5
[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.
★ 1,378+0Star change over the last 7 days - #6
Fun-Audio-Chat is a Large Audio Language Model built for natural, low-latency voice interactions.
★ 1,002+5Star change over the last 7 days
