Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine

Generate audiobooks from e-books

SoulX-FlashTalk is the first 14B model to achieve sub-second start-up latency (0.87s) while maintaining a real-time throughput of 32 FPS on an 8xH800 node.

Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.

Official inference code for SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

High-quality speech synthesis with LoRA fine-tuning on index-tts, enhancing prosody and naturalness for single and multi-speaker voices.

Text Normalization & Inverse Text Normalization

MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and the OpenMOSS team. With only 0.1B parameters, it is designed for realtime speech generation, can run direc…

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

Chinese text normalization for speech processing

High-Quality Voice Cloning TTS for 600+ Languages

Easy to use stem (e.g. instrumental/vocals) separation from CLI or as a python package, using a variety of amazing pre-trained models (primarily from UVR)

Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching

Spark-TTS Inference Code

F5-TTS 推理加速，速度提升约4倍！

TTS with kokoro and onnx runtime

State-of-the-art TTS model under 25MB 😻

Open Source Speech Language Model

自动直播录制、投稿、twitch、ytb频道搬运工具。命令行投稿(B站)和视频下载工具，提供多种登录方式，支持多p。

PersonaPlex code.

🚀🎬灵活、高效、可扩展，专属剪辑配音工具箱，释放创作潜力 . Flexible, efficient, and scalable toolbox for editing and dubbing, unleashing creative potential

LongLive 2.0: Infra - Long Video Gen

[ECCV 2026] Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"