Comfyui Voice Generator

Provided by TippyEntertainment

https://github.com/tippyentertainment/skills.git

This skill is designed for use on the Tasking.tech agent platform (https://tasking.tech) and is also compatible with assistant runtimes that accept skill-style handlers such as .claude, .openai, and .mistral. Use this skill for both Claude code and Tasking.tech agent source.

Provided by Tippyentertainment/skills.git

comfyui-voice-generator

Summary

Generate AI voice‑overs and character lines using ComfyUI‑orchestrated TTS or voice models. This skill turns scripts and character briefs into audio files that can be synced with AI‑generated video scenes.

When to Use

• The user wants narration, dialogue, or character voices for an AI video or game.
• The user provides a script and asks for it to be read in a specific style (narrator, announcer, character).
• You are building a trailer, explainer, or “AI movie” and need spoken lines.

Inputs to Collect

Ask the user for:

• Script text
  • Exact words to be spoken; can be a single line or a full paragraph.
• Voice type
  • Narrator / character / announcer / child / elderly, etc.
• Gender / pitch / tone (optional)
  • Masculine/feminine/androgynous, high/medium/low pitch, calm/excited/serious/playful.
• Accent / language
  • Language (e.g., en‑US, en‑GB, ja‑JP) and any accent preference.
• Emotion / delivery
  • Neutral, dramatic, whispery, humorous, inspirational, etc.
• Pacing
  • Slow / normal / fast; “podcast‑like”, “trailer voice”, etc.
• Target usage
  • Which clip or scene ID this VO is for, and any timing constra