QwenAudio/ThinkSound

[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.

Owner: QwenAudio (organization)
Stars: Stars: 1,384
Forks: Forks: 81
Language: Python
License: None
Created: 2025
Topics: aigc-audiofoley-sound-synthesistext-to-audiotext-video-to-audiottavideo-to-audio
Tier: Beta (700 to 1,999 ★) What this tier means

View on GitHub

More repos by QwenAudio

All 9 repos by QwenAudio

QwenAudio/CosyVoiceStars: 24,238PythonLTS
QwenAudio/SenseVoiceStars: 9,667CStable
QwenAudio/qwen-audio-agentStars: 3,101JavaScriptRC
QwenAudio/Fun-ASRStars: 1,595CBeta
QwenAudio/Fun-Audio-ChatStars: 1,010PythonBeta
QwenAudio/FunCineForgeStars: 457PythonAlpha

Nearby in Python

All Python repos

bytedance/music_source_separationStars: 1,384PythonBeta
keyu-tian/SparKStars: 1,384PythonBeta
HazyResearch/minionsStars: 1,384PythonBeta
CIRCL/AIL-frameworkStars: 1,384PythonBeta
dthpham/sminterpolateStars: 1,384PythonBeta
liriansu-opus/chinese-calendarStars: 1,384PythonBeta