창작 및 미디어 · GitHub

Stemdeck is an modern stem extraction platform for musicians,producers and hobbyists, designed to isolate vocals, drums, bass, piano and guitar for practice, transcription, remixing, and creative audio workflows through a modern and interactive interface

Termux용 X 서버 애드온.

간편한 동영상 편집!

이미지와 동영상의 하드코딩된 자막 및 텍스트 워터마크를 AI로 제거하고, 원본 해상도를 유지한 자막·워터마크 제거 파일을 생성하는 도구입니다. 타사 API 신청 없이 로컬에서 실행할 수 있습니다.

A blazingly fast programmatic video engine, made for agents.

Musicdl은 순수 Python으로 작성된 경량 음악 다운로더입니다. NetEase Cloud Music, QQ Music, Kugou Music, Kuwo Music, Migu Music, Qianqian Music, Soda Music, Bilibili, StreetVoice, Ximalaya, Lazy Audio, Lizhi FM, Qingting FM, JOOX, TIDAL, YouTube, Apple Music, Spotify, Qobuz, SoundCloud 등 수십 개의 음악 및 오디오북 플랫폼에서 무손실 음원을 다운로드할 수 있습니다.

CVAT는 이미지, 비디오, 오디오, 3D 데이터셋을 위한 선도적인 데이터 어노테이션 플랫폼입니다. 오픈 소스, 클라우드, 엔터프라이즈 제품과 라벨링 서비스를 제공하며, AI 지원 라벨링, 품질 보증, 팀 협업, 분석, 개발자 API를 갖추고 있습니다.

• Manual & Auto-labeling: Annotate images, videos, audio, and 3D point clouds with bounding boxes, polygons, masks, keypoints, cuboids, tags, intervals and more. Speed up labeling by connecting your own models for automatic annotation.
• Task Management: Organize datasets into projects, split them into tasks and jobs, assign work to annotators, and track progress in real time.

Seedance2.0으로 동영상을 생성하기 위한 최적의 프롬프트를 만드는 스킬입니다.

"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"

• Idea2Video — turn a short concept into structured stories, characters, scripts, storyboards, shots, and a finished video.
• Script2Video — convert an explicit screenplay into controllable multi-scene, multi-shot video while preserving its creative intent.

BaoCut: 편집 가능한 타임라인을 갖춘 AI 동영상 에이전트입니다. 동영상 받아쓰기, 자막 제작, 번역, 더빙, 편집, 애니메이션 제작을 할 수 있습니다.

• Transcribe with local models (Whisper large-v3 / v3-turbo, Qwen3-ASR, MOSS with diarization) or online APIs, with word-level timing. Segments stream into the timeline while the job runs.
• Subtitle in the original language, translated, or bilingual. The agent translates sentence by sentence itself; subtitle styles are remembered per project.

Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis

• Multimodal perception — Claude sees video frames directly and reads audio transcriptions with timestamps
• YouTube URL support — Pass a YouTube URL directly; the MCP server downloads it with yt-dlp, preserving source metadata and captions for context

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Restore videos with pixelated/mosaic regions

• Recover Pixelated Videos: Restore pixelated or mosaic scenes in adult videos.
• Watch/Export Videos: Use either the CLI or GUI to watch or export your restored videos.

A script allowing you to download images and videos from Telegram web even if the group restricts downloading.