Self host / Open Sources AI tools

The following section will be focus on self-hosting AI tools, which aims to free forever or open to host with your own devices.

Platform

- Dify.AI

The Innovation Engine for Generative AI Applications
https://dify.ai/ (opens in a new tab)

- langflow

Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.
https://www.langflow.org/ (opens in a new tab)

Audio to Text

- Whisper

High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
https://github.com/Const-me/Whisper (opens in a new tab)

- buzz

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
https://github.com/chidiwilliams/buzz (opens in a new tab)

Text to Images / Video

- stable-diffusion-webui

Stable Diffusion web UI.
https://github.com/AUTOMATIC1111/stable-diffusion-webui (opens in a new tab)

- invokeAi

InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies.
https://github.com/invoke-ai/InvokeAI (opens in a new tab)

- ComfyUI

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.
https://github.com/comfyanonymous/ComfyUI (opens in a new tab)

Audio to Audio

- Ultimate Vocal Remover

GUI for a Vocal Remover that uses Deep Neural Networks.
https://github.com/Anjok07/ultimatevocalremovergui (opens in a new tab)

- Retrieval-based-Voice-Conversion-WebUI

Easily train a good VC model with voice data within 10 mins!
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI (opens in a new tab)

Prompt To Text

- ollama

Get up and running with large language models.
https://ollama.com/ (opens in a new tab)