Text Echo Chamber: Audio Drama Script Inspiration Generator

Problem

Audio drama and radio scripts often get stuck on sound design: the plot exists, but environmental cues, transitions, vocal tone, and narrator pauses lack actionable annotations. Recording immediately is expensive and slow to revise, making it a poor fit for early emotional-rhythm exploration.

How It Works

This skill treats text as a soundstage, organizing output around four layers: the sound-effects layer for ambience and action cues, the dialogue layer for lines, narration, and inner OS, the pacing layer for emotional progression and silence, and the prompt layer for performer directions such as tempo, breath, and pauses. The workflow starts with soundstage diagnosis, detecting existing 【sound: xxx】 markers, character lines, system voice, and prompts, then selects a generation mode: one-click soundstaging, expansion, dialogue polishing, scene construction, style imitation, or audiobook optimization. It also provides descriptive vocabulary for environmental, action, and transition sounds, plus annotation terms for volume, speed, timbre, and emotion, turning abstract cues like “grief” or “distant to near” into script-ready language. With genre templates for xianxia, urban, suspense, sci-fi, and historical settings, it helps produce a structured audio-drama script before recording and post-production.

Boundaries

It generates text-based soundstage scripts and performance prompts, not audio files, and it does not synthesize, record, or mix sound. It is suitable for early script design, narrator direction, style reference, and fast iteration; final broadcast still requires real recording, sound assets, and post-production.