v3ucn
Follow
-
higgs-audio_quantized Public
Forked from Nyarlth/higgs-audio_quantizedQuantized text-audio foundation model from Boson AI
Python UpdatedJul 23, 2025 -
-
coqui-ai-TTS Public
Forked from idiap/coqui-ai-TTS🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Python Mozilla Public License 2.0 UpdatedJul 18, 2025 -
LstmSync Public
Forked from oneCodeSuperman/LstmSync开源的LstmSync数字人泛化模型，只做最好的泛化模型！
-
index-tts-vllm Public
Forked from Ksuriuri/index-tts-vllmAdded vLLM support to IndexTTS for faster inference.
-
-
Hunyuan3D-2.1 Public
Forked from Deathdadev/Hunyuan3D-2.1From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
-
gtcrn Public
Forked from Xiaobin-Rong/gtcrnThe official implementation of GTCRN, an ultra-lightweight SE model.
Python MIT License UpdatedMay 28, 2025 -
-
HeyGem-Linux-Python-Hack Public
Forked from Holasyb918/HeyGem-Linux-Python-HackA docker free offline version for HeyGem; Python and Linux is all you need!
-
Fast-Spark-TTS Public
Forked from HuiResearch/FlashTTS基于SparkTTS模型，提供高质量中文语音合成与声音克隆服务。
-
Spark-TTS Public
Forked from SparkAudio/Spark-TTSSpark-TTS Inference Code
Python Apache License 2.0 UpdatedMar 5, 2025 -
Step-Audio-tts Public
Forked from Harry-Yu-Shuhang/Step-Audio-tts -
local-llasa-tts-windows Public
Forked from justinjohn0306/local-llasa-tts-windowsExamples of using the llasa-tts models locally
Jupyter Notebook UpdatedFeb 4, 2025 -
GPT-SoVITS Public
Forked from RVC-Boss/GPT-SoVITS1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
-
bailing Public
Forked from wwbin2017/bailing百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，时延低至800ms，低配置也可运行，支持打断
-
espeakng-loader Public
Forked from thewh1teagle/espeakng-loaderThis package loads the espeak-ng shared library so it will be available for other libraries.
Python UpdatedJan 17, 2025 -
GPT-SoVITS-V2 Public
GPT-SoVITS-V2模型，合并了官方的一些PR，包含但不限于:参考音频自动填充，字幕同步，SillyTavern酒馆接入等功能
-
LatentSync Public
Forked from bytedance/LatentSyncTaming Stable Diffusion for Lip Sync!
Python Apache License 2.0 UpdatedJan 10, 2025 -
-
CosyVoice Public
Forked from FunAudioLLM/CosyVoiceMulti-lingual large voice generation model, providing inference, training and deployment full-stack ability.
-
基于Faster-whisper和modelscope一键生成双语字幕，双语字幕生成器,基于离线大模型,Generate bilingual subtitles with one click based on Faster-whisper and modelscope. Off-line large model
-
CosyVoice_For_Windows Public
CosyVoice在Windows环境下使用的版本
-
-
MeloTTS-ONNX Public
Forked from season-studio/MeloTTS-ONNXAn implementation of MeloTTS by onnxruntime
Python MIT License UpdatedOct 27, 2024 -
F5-TTS Public
Forked from SWivid/F5-TTSOfficial code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
-
digital_human_video_player Public
Forked from Ikaros-521/digital_human_video_player洛曦 数字人视频播放器，带HTTP API，使用gradio api对接Easy-Wav2Lip、Sadtalker、GeneFacePlusPlus、MuseTalk，也可以用于播放本地视频
-
oh-my-live2d Public
Forked from oh-my-live2d/oh-my-live2d应用于浏览器环境且开箱即用的Live2D组件, 它支持所有版本的Live2D模型, 使用方式足够简单并且高可自定义, 可以快速为您的个人网站添加Live2D看板娘, 使您的个人网站变得更具有特色.
-
Ultralight-Digital-Human Public
Forked from anliyuan/Ultralight-Digital-Human一个超轻量级、可以在移动端实时运行的数字人模型
-
SillyTavern Public
Forked from SillyTavern/SillyTavernLLM Frontend for Power Users.