Awesome Opensource Ai

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

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

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Open-Source Frontier Voice AI

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

Making large AI models cheaper, faster and more accessible

A generative speech model for daily dialogue.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

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

SOTA Open Source TTS

🤗 smolagents: a barebones library for agents that think in code.

Generative Models by Stability AI

SoTA open-source TTS

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.

An open-source RAG-based tool for chatting with your documents.

A simple screen parsing tool towards pure vision based GUI agent

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.

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

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

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

A TTS model capable of generating ultra-realistic dialogue in one pass.

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.

No description.

The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Go ahead and axolotl questions

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

AI Observability & Evaluation

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

MiniCPM5: SOTA on-device LLMs, small yet powerful.

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

tiny vision language model

ModelScope: bring the notion of Model-as-a-Service to life.

PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

[SIGMOD'27] Easy Data Preparation with latest LLMs-based Operators and Pipelines.

Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.

Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 2,200+ medical models, 21 languages, Apple MLX + Python, no cloud, no patient data leaving your network. Apache-2.0

AutoRAG: Now your agent can find anything in your computer. It gets smarter if you are using it frequently.