Generate **background music** and **ambience** that matches one or more video scenes produced by `comfyui-video-generator`. This skill does *not* handle spoken dialogue or narration; use `comfyui-voice-generator` for any voice work.
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.
Generate background music and ambience that matches one or more video scenes produced by comfyui-video-generator. This skill does not handle spoken dialogue or narration; use comfyui-voice-generator for any voice work.
Ask the user (or previous skill) for:
music or ambience (no voice).comfyui-video-generator (IDs, durations, moods).audioType, genre, mood, durationSeconds, loopable, targetScenes, tempo, intensity.audioUrl / audioPathdurationSecondsformat, sampleRate, channelsReturn a structure containing:
description: e.g. “Loopable synthwave track for the opening scene.”audioUrl or audioPathdurationSecondsformatsampleRatechannelsloopable: booleantags: list of strings (genre, mood, tempo)Typical pipeline:
comfyui-video-generator → create scenes.comfyui-audio-creator → create background music/ambience for those scenes.comfyui-voice-generator → add narration or dialogue.comfyui-soundfx-creator → layer in moment‑specific sound effects.This skill focuses on non‑voice background audio so other skills can handle speech and SFX cleanly.