FFmpeg plugins

Author animated video compositions in HTML using GSAP, Tailwind, Three.js, Lottie, Web Animations API; add AI-generated TTS voiceovers, Whisper captions, audio-reactive visuals; preprocess media; preview, lint, and render via CLI; capture websites or migrate Remotion projects to video.

Engage in natural voice conversations with Claude Code using local Whisper speech-to-text and Kokoro text-to-speech. Auto-activate via mentions or commands, play background music, clone custom voices from clips, connect remotely to iOS/web clients, install dependencies, and monitor service status.

Have Claude analyze any video from YouTube, Vimeo, TikTok, or local files: it downloads with yt-dlp, extracts frames via ffmpeg, transcribes using captions or Whisper, then answers questions grounded in visuals and audio transcript.

Enable Claude to analyze local video files or YouTube URLs with full multimodal perception: extract frames and audio via FFmpeg, detect scenes/motion/silence/transitions, transcribe speech using Whisper or Gemini, generate detailed visual descriptions, summaries, and answer questions interactively.

Automate Chinese legal workflows by converting PDFs/images to structured Markdown via OCR, transcribing audio/video with speaker diarization, generating professional reports/contracts/case analyses, organizing case files into standardized directories, extracting patent claims, querying legal databases/APIs, and formatting statutes/judgments.

Automate full music album workflows with Suno AI: design concepts and tracklists across 7 phases, research themes, generate lyrics with prosody checks, craft V5 prompts, import/process/master audio, create promo videos and social copy, validate QA gates, and release to streaming platforms with asset uploads.

Generate polished podcast episodes with TTS narration, rich timelines including chapters images links and Spotify entities, cover art, and raw media uploads, then publish them directly to Spotify shows via CLI.

Equip Claude Code with 18 specialized AI skills to orchestrate complex tasks via plugin discovery and execution plans, conduct deep web research with citations, design software architectures using C4 diagrams, process and transcribe audio/video/content files, optimize LLM prompts, and create custom skills.

Generate section-by-section Markdown study notes from any video URL or local file, embedding screenshots and timestamped transcripts, with optional focus on specific topics or questions via AI analysis. Initialize sessions by running custom bash scripts.

Download videos from 1800+ platforms like YouTube, TikTok, and Twitter, then auto-generate MP4 files, MP3 audio extracts, VTT subtitles, TXT transcripts, and Markdown AI summaries. Everything saves directly to your downloads folder for easy access and reuse in projects.

Automate video editing and rendering with FFmpeg and Remotion by stitching clips, adding transitions, captions, teasers, and Whisper transcription. Generate professional AI infographics from natural language or content analysis using Gemini. Conversationally design Excalidraw presentations, diagrams, and slide decks, exporting JSON or injecting into excalidraw.com via browser automation.

Generate visuals across 11 channels including raster, SVG, web, interactive, video, terminal, diagrams, and infographics while enforcing brand tokens, 8:1 contrast minimum, custom dimensions, and style guides. Critique produced PNG/JPG/SVG/PDF artifacts with a vision-model agent that evaluates design principles (Tufte/Bertin/Gestalt), channel anti-patterns, and brand compliance, providing evidence-based PASS/NEEDS REVISION/FAIL verdicts.

Record TikTok-style MP4 videos walkthroughing your local dev server UI on ports like 3000/5173/8080, scaffold tiktest.md configs automatically from README/package.json, run checks-only validation passes without rendering, and summarize changes via tik-test CLI.

Develop, debug, and deploy Home Assistant automations, custom Python integrations, Lovelace dashboards, Docker add-ons, Assist voice control, energy monitoring setups, and REST/WebSocket API connections using specialized skills, commands, and agents.

Automate daily life, career, and productivity tasks with AI agent skills that scrape badminton courts and Google Maps, track cashflow to Notion and Obsidian, analyze job-CV fits, monitor AI token usage across providers, audit social media engagement, and sync test cases to BrowserStack via natural language triggers.

Extract keyframes from videos using FFmpeg scene detection and transcribe audio with optional Whisper to enable Claude to analyze screen recordings, bug reports, tutorials, and demos. Process the latest video from common folders like Desktop or Downloads, set custom directories, or analyze specific files via commands.

Automate audio production with ElevenLabs API for TTS speech, sound effects, and voice cloning via commands and skills. Edit videos and audio using FFmpeg for conversion, trimming, overlays, and mixing. Clean raw footage by AI-detecting silences, retakes, and duplicates with Whisper, then regenerate narration using custom TTS.

Select, implement, review, and migrate Rust FFmpeg libraries like ez-ffmpeg and ffmpeg-next to build video/audio processing pipelines, handle media conversion, and tackle multimedia tasks with guided code generation and problem-solving workflows.