FunASR
Verified · 41 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Self-hosted MCP server: video lipsync, face restore, and ffmpeg ops (trim, concat, transcode).
claude mcp add flickies -- docker run -i --rm docker.io/psyb0t/flickies:v0.3.17
Self-hosted media-processing server for lip-sync, face restoration, and general ffmpeg operations such as trimming, concatenation, and transcoding. It targets creators or automation builders who need video post-processing available to agents in a local or containerized setup. The feature set is broader than a simple wrapper, but these pipelines are resource-intensive and quality will likely vary by model choices and host environment.
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Identify and remove AI watermarks and provenance metadata from your own images and video.
Turn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.
Trim, convert, resize, compress, and remix audio and video.
Screen recording, meeting notes, and voice dictation - all with AI