
ffmpeg-skill
MCP serverLocal FFmpeg video and audio editing tools for coding agents over MCP
Runs locally- Open source
- 7.8K GitHub stars
- Design and media

Local FFmpeg video and audio editing tools for coding agents over MCP
Runs locallyVoice AI from Cartesia: text-to-speech, transcription, voice cloning and pronunciation
Not checked yetConvert audio, PDF, photos and text into chord sheets and manage a Jam Jam songbook
Runs locallyMCP server that converts one local file per call using mdisbetter.com and an API key
Runs locallyQuote, then generate images, video and audio with 500+ models and user-approved spend
Not checked yetMCP server for Audial's stem splitting, mastering, MIDI, lyrics and music generation
Runs locallyGenerate images, video and audio, lip-sync, dub and upscale from your AI assistant
Not checked yetLocal MCP server that transcribes audio and video files with Whisper or OpenAI
Runs locallyLocal transcription, summaries and edits for video links and audio files
Runs locallyLoudness, true-peak and voice-quality measurements for audio files, as MCP tools
Runs locallyRun any WaveSpeed image, video, audio or 3D model from an MCP client, quoting price first
Not checked yetMCP server that dubs YouTube videos or SRT files, with one cloned voice per speaker
Runs locallyHosted MCP server that gives AI clients Speechmatics speech-to-text for audio and video
Not checked yetTurn scripts into voiceover audio with matching SRT and VTT subtitles
Runs locallyGenerate AI video, images and audio from your agent using AIVeed credits
Runs locallyThai, English and Mandarin text to speech, transcription, OCR and translation
Runs locallyPaid human listeners judge your TTS audio in blind preference or human-vs-AI studies
Runs locallyStrips AI-baked background music from video clips while keeping dialogue and sound effects
Runs locallyCompress images, PDFs, video, audio and archives from your AI assistant
Not checked yetWatermark and C2PA-sign AI-generated images and audio, and verify marked files
Runs locallyGive an assistant a voice: text to speech in about 190 voices, cloud or local
Runs locallyGive an AI assistant text to speech in about 190 voices, hosted or fully offline
Not checked yetFind ad templates, price a job first, then render video, image and audio from an assistant
Not checked yetCloud Blender rendering, asset search and 3D, image and audio tools for agents
Runs locally
Generate images, video and audio from your agent with Kubflow credits
Not checked yetTurn scripts into validated voice across 30+ TTS models, with pronunciation fixes
Not checked yetSplit stems, clean vocals and train or apply RVC voices from an agent
Not checked yetLet Claude read and mix a REAPER session, with every change inside an undo block
Runs locallyTranscribe audio and video into speaker-labelled transcripts, subtitles and cited Q&A
Not checked yetPrivate on-device speech to text for AI assistants: transcribe files, search dictations
Runs locally