Comfyui Voice Pipeline
Wire speech-to-text, TTS, and audio nodes into ComfyUI graphs for voiced avatars, narrated renders, and multimodal generative pipelines.
npx skills add https://github.com/mckruz/comfyui-expert --skill comfyui-voice-pipeline| Installs | 151 |
|---|---|
| Repository | mckruz/comfyui-expert ↗ |
Related skills
Ai Video GenerationGenerate short-form and marketing videos from prompts or reference images without leaving your agent, using inference.sh belt and 40+ models.300k512Remotion RenderTurn Remotion/React TSX components into MP4s through belt so your agent can ship motion graphics and data-driven videos from code.299k512Ai Image GenerationGenerate product mockups, marketing visuals, and social graphics from text prompts without leaving your agent workflow.299k512Ai Avatar VideoProduce talking-head and UGC-style avatar videos from text or audio for explainers, ads, and virtual presenters via belt CLI.299k512
Video EditRoute natural-language video edit requests to the right RunComfy edit model and run jobs through the local RunComfy CLI without guessing which endpoint fits each transform.252k15Image To VideoAnimate still images via RunComfy by routing to HappyHorse, Wan 2.7, or Seedance i2v models.251k15