Native Node.js addon for capturing per-app audio on macOS using ScreenCaptureKit. Real-time audio streaming with event-based API

Digital Mind Extension

A Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows

HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

Official codebase for the paper "Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations"

Media over QUIC Transport Implementation

MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows

Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

Krea Realtime 14B. An open-source realtime AI video model.

​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

Text to speech alignment using CTC forced alignment

realtime message based on socketio and redis

Realtime Audio SDK for the Web — audio capture, echo cancellation (AEC), voice activity detection (VAD), and real-time encoding (Opus/PCM).

The official implementation of GTCRN, an ultra-lightweight SE model.

LoRA-based phoneme/prosody control for LLM-based TTS with no G2P - Lightweight adapter for edit and control the target language's phoneme-level pronunciation and prosody while preserving other lang…

Wan: Open and Advanced Large-Scale Video Generative Models

Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

A Unified Framework for Expressive Speech Synthesis with Voice Cloning

Text-audio foundation model from Boson AI

iikira/BaiduPCS-Go原版基础上集成了分享链接/秒传链接转存功能

一个面向中文文本纠错任务的综合平台，集学术研究、模型训练、模型评测和推理部署于一体，覆盖拼写纠错与语法纠错两个核心方向。

The TypeScript AI agent framework. ⚡ Assistants, RAG, observability. Supports any LLM: GPT-4, Claude, Gemini, Llama.

A codebase for data crawling and preprocessing for TTS and ASR systems training.

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.

VoiceBench: Benchmarking LLM-Based Voice Assistants