超好用的截图工具 snow-shot

将视频从一种语言翻译为另一种语言，同时支持语音识别转录、语音合成、字幕翻译。 Translate the video from one language to another and add dubbing.

A lightweight LMM-based Document Parsing Model

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…

"RAG-Anything: All-in-One RAG System"

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

基于音频的多人对话视频生成技术-Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

Office PowerPoint(.pptx) file to JSON | 将 PPTX 文件转为可读的 JSON 数据

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

流式2D数字人

各领域开发学习路线，互动式路线图、指南以及其他教育内容，助力开发者的职业发展。

LiveCC：大规模流式语音转录学习视频语言模型（CVPR 2025）

1分钟的语音数据也可以用来训练一个很好的TTS模型！（少量镜头语音克隆）

一个简单的本地网页界面，使用ChatTTS将文字合成为语音，同时支持对外提供API接口。A simple native web interface that uses ChatTTS to synthesize text into speech, along with support for external API interfaces.

heygem.ai云端合成封装代码示例

🎬 卡卡字幕助手 | VideoCaptioner - 基于 LLM 的智能字幕助手 - 视频字幕生成、断句、校正、字幕翻译全流程处理！- A powered tool for easy and efficient video subtitling.

实时对话2D数字人，可识别物体

Spark-TTS 推理代码

Triton-Windows-GPU优化-模型加速Fork of the Triton language and compiler for Windows support and easy installation

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

250319-A powerful tool for creating fine-tuning datasets for LLM

HeyGen平替-HeyGem

文字转语音-用于日常对话的生成式语音模型。- A generative speech model for daily dialogue.

微信视频号下载工具，支持视频、直播回放、直播下载

一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。A high-quality tool for convert PDF to Markdown and JSON.

mash up of Wan2.1 + Meta Sapiens + Seaweed Diffusion APT for One-Step Video Generation if you have compute - call me

视频生成用的数字人-基于分层音频-动作嵌入和扩散插值的协同语音手势视频重演

wav2lip384生成器网格权重——来自不蠢不蠢

LLaMA-Factory微调-Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

"LightRAG: Simple and Fast Retrieval-Augmented Generation"