Speaker diarization, voice enrollment, and identification for audio files — builds a local voiceprint library with optional cloud replication.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin audio-voice-id in danielrosehill/audio-voice-id-plugin. Commands read from the repo's manifest — 1 month ago.
/audio-voice-id:diarization:diarize-audioRun pyannote speaker diarization on an audio file and emit RTTM + JSON with per-segment speaker labels
/audio-voice-id:diarization:label-diarizationMatch diarization speakers against the enrolled voice library and rewrite labels with real names
/audio-voice-id:enroll:enroll-from-diarizationEnroll a voice by extracting a specific diarized speaker's segments from the original audio
/audio-voice-id:enroll:enroll-voiceEnroll a named voice from a clean audio clip (or multiple clips) — computes and stores an ECAPA embedding
/audio-voice-id:identify:identify-voiceIdentify the speaker in a single-speaker audio clip against the enrolled library
/audio-voice-id:install:install-diarizationInstall pyannote.audio and SpeechBrain for diarization and speaker embeddings
/audio-voice-id:library:delete-voiceDelete an enrolled voice from the library (destructive — requires confirmation)
/audio-voice-id:library:list-voicesList all enrolled voices in the local library with sample counts, durations, and last-updated dates
/audio-voice-id:library:rename-voiceRename an enrolled voice (updates directory, library.json, and meta.json)
/audio-voice-id:library:setup-voice-libraryCreate the local voice-print library directory and (optionally) configure a cloud rclone remote for replication
/audio-voice-id:library:sync-voice-libraryPush or pull the local voice library to/from the configured rclone cloud remote
AI music generation via Cognitum Music (cogmusic MCP) — compose lyrics/prompts, generate tracks, separate stems, extract MIDI, and master through your own music.cognitum.one account
7 skills · 1 command · 2 agents
HyperFrames by HeyGen. Write HTML, render video. Compositions, GSAP and runtime adapter animations, captions, voiceovers, audio-reactive visuals, and website-to-video capture for HyperFrames.
34 skills
Convert common image, audio, video, document, and data formats with installed local tools while preserving originals.
1 skill
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
1 skill · 2 commands · 2 agents · hooks
Google NotebookLM browser-automation skill. 4 actions (read/extract, add-source, Studio outputs, create notebook). Screenshot-first + find-before-click + fire-and-notify async discipline. Path-B from megaprompt 03.
1 skill · 1 command · 1 agent
Vision, audio, and multimodal models including CLIP, Whisper, LLaVA, BLIP-2, Segment Anything, Stable Diffusion, AudioCraft, Cosmos Policy, OpenPI, and OpenVLA-OFT. Use when working with images, audio, multimodal tasks, or vision-language-action robot policies.
98 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.