Store

Multi-Identity Consistency for Image Customization via Matching Reward https://github.com/bytedance/UMO

# SillyTavern Character Generator A pinokio script for https://github.com/Tremontaine/character-card-generator When used with KoboldCPP use http://localhost:5001/v1 Where 5001 is the port reported by KoboldCPP when starting Text API Key needs to be filled with anything. (If left empty will give a error so just add anything to it)

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

AI-powered speech denoising + enhancement (Gradio web demo + CLI).

🎙️ Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning. High-quality text-to-speech synthesis supporting zero-shot voice cloning and streaming inference with natural emotional expression.

AI Toolkit by Ostris

Voice Synthesis Platform with Smart Chunking, Batch Processing, and Voice Cloning capabilities.

1 Click Installer for Retrieval-based-Voice-Conversion-WebUI (https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)

Fast Speech-to-Text Web UI with Apple MLX and OpenAI Whisper

🎙️ Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning. Features 44.1kHz sampling rate, 6.25Hz token rate, and supports both SFT and LoRA fine-tuning. Built on MiniCPM-4 backbone for highly expressive, natural speech synthesis.

自动化上传视频到社交媒体：抖音、小红书、视频号、tiktok、youtube、bilibili

Dia is a 1.6B parameter text to speech model created by Nari Labs. Dia directly generates highly realistic dialogue from a transcript. You can condition the output on audio, enabling emotion and tone control. The model can also produce nonverbal communications like laughter, coughing, clearing throat, etc. https://github.com/nari-labs/dia

[v0.5.1] FramePack Video App offering multiple generation types: Original, F1, video extension, end frame. Features include: LoRA support, job queueing, advanced timestamped prompts, offline mode, a post-processing suite including upscaling, interpolation, filters and more!

A web interface for managing and interacting with Ollama models

Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers. https://github.com/Zyphra/Zonos

Prompt, run, edit, and deploy full-stack web apps. https://github.com/stackblitz-labs/bolt.diy

Automatically create music videos. Synchronize the cuts to the music's beat.

A Step Towards Music Generation Foundation Model

[NVIDIA ONLY] Make virtual avatars talk whatever you want with an image and an audio clip https://github.com/antgroup/echomimic_v2

Gradio web interface for Photoroom's PRX-1024-t2i-beta text-to-image model