Best GitHub Repos

The 22 best GitHub repos for media & audio

Browse all top repos for media & audio

22 repos

Whisper

★ 108k · Python · Active

Robust Speech Recognition via Large-Scale Weak Supervision

Media & audio

ComfyUI

★ 129k · Python · Active

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Media & audioSelf-hosted apps

MoneyPrinterTurbo

★ 115k · Python · Active

利用 AI 大模型和自动化工作流,根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

Media & audio

Manim

★ 92k · Python · Active

Animation engine for explanatory math videos

Media & audio

FFmpeg

★ 63k · C · Active

Mirror of https://git.ffmpeg.org/ffmpeg.git

Media & audio

Remotion

★ 56k · TypeScript · Active

Make videos programmatically with React

Media & audio

Fooocus

★ 52k · Python

Focus on prompting and generating

Media & audioSelf-hosted apps

OpenMontage

★ 48k · Python · Active

World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files.

Media & audio

VoxCPM

★ 36k · Python · Active

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

Media & audio

Handy

★ 30k · Rust · Active

A free, open source, and extensible speech-to-text application that works completely offline.

Media & audio

Buzz

★ 29k · Rust · Active

A hive mind communication platform

Media & audio

Open Generative Ai

★ 27k · JavaScript · Active

Unrestricted Open-source alternative to AI video platforms, Free AI image & video generation studio with 500+ models (Flux, Midjourney, Kling, Sora…

Media & audio

Faster Whisper

★ 25k · Python

Faster Whisper transcription with CTranslate2

Media & audio

Index Tts

★ 23k · Python · Active

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Media & audio

Wan 2.1

★ 17k · Python

Wan: Open and Advanced Large-Scale Video Generative Models

Media & audio

Duix Avatar

★ 15k · C

Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.

Media & audio

Pipecat

★ 15k · Python · Active

Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.

Media & audio

Supertonic

★ 14k · Swift · Active

Lightning-Fast, On-Device, Multilingual TTS, running natively via ONNX.

Media & audio

FluidVoice

★ 11k · Swift · Active

Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. A local Wispr Flow alternative.

Media & audio

OmniVoice

★ 9.3k · Python · Active

High-Quality Voice Cloning TTS for 600+ Languages

Media & audio

PersonaLive

★ 3.5k · Python

[CVPR 2026] PersonaLive!: Expressive Portrait Image Animation for Live Streaming

Media & audio

AutoClip

★ 984 · Python

AutoClip: AI-powered video clipping and highlight generation · 一款智能高光提取与剪辑的二创工具

Media & audio