Wanted

Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 24kHz audio quality

GUI for Faster‑Whisper‑XXL transcription tool: download YouTube audio, transcribe local files, manage models, and export multiple formats with themes and auto yt‑dlp updates.

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

Contribute to Shao-Music-AI/Shao development by creating an account on GitHub.

High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance

A general-purpose AIGC video engine: script to finished film in one pipeline — dramas, ads, product videos, otome games, and more. | 通用 AIGC 视频引擎 —— 从剧本到成片一条流水线，漫剧、广告、电商、乙游皆可

FinRL-X: An AI-Native Modular Infrastructure for Quantitative Trading

High-Quality Voice Cloning TTS for 600+ Languages

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

The open-source CapCut alternative

✂️ Open-source, self-hosted Opus Clip alternative. Turn long YouTube videos or uploads into viral 9:16 vertical shorts: AI viral-moment detection (Gemini), auto transcription + subtitles, active-speaker reframing, in-browser editing, and one-click TikTok / Reels / Shorts scheduling.

Simple Qwen3-VL gguf model loader for Comfy-UI.

An autonomous agent that conducts deep research on any data using any LLM providers.

Seedance 2.0 is a revolutionary multi-modal video generation model that bridges the gap between AI and professional filmmaking. This repository provides the official Python client for interacting with the Seedance API.

Never stop coding. Free AI gateway: one endpoint, 160+ providers (50+ free), connect Claude Code, Codex, Cursor, Cline & Copilot to FREE Claude/GPT/Gemini. RTK+Caveman stacked compression saves 15-95% tokens, smart auto-fallback, MCP/A2A, multimodal APIs, Desktop/PWA.

Turn hand-drawn story illustrations into 35–45 second line-reveal and gradual-coloring videos with HyperFrames.

Think with AI beyond the chat box. A shared canvas for handwriting, equations, diagrams, and spatial reasoning.

[NeurIPS 2025] Pixel-Perfect Depth

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction method. 🤝🤖 It integrates various technologies like Whisper, Linly, Microsoft Speech Services, and SadTalker talking head generation system. 🌟🔬