Automate multi-character Chinese radio drama production from script to final MP3.
npx skills add https://github.com/FatOtter/project-jupiter --skill radio-drama
Please help me install this Agent Skill. Skill: radio-drama Source: https://github.com/FatOtter/project-jupiter/tree/main/.opencode/skills/radio-drama Command: npx skills add https://github.com/FatOtter/project-jupiter --skill radio-drama
Radio drama production is complex, requiring scripting, voice design, SFX coordination, and precise mixing across multiple segments. This Skill centralizes the workflow with a clear project layout, automated steps, and reusable templates to accelerate creation and ensure consistent results.
Provide a project brief with characters and a sample script, and this skill will produce the full radio drama with TTS voices, SFX, and a final mixed MP3.
High-intent search queries and answers about installing and using this skill.
Automating multi-character radio drama production involves using a scripted pipeline to generate TTS voices, apply SFX from an asset library, and mix segments into a final MP3. This workflow centralizes voice design and audio mixing.
The end-to-end radio drama workflow progresses from scripting and voice design to segment-based TTS generation, audio splitting, SFX mixing, and final MP3 export. It requires a defined project layout with character and SFX libraries.
Yes, mixing radio dramas with TTS voices requires a defined project layout. You must set up specific directories for characters, an SFX library, and a radio_drama path to ensure the automation workflow functions correctly.
Yes, you can use ComfyUI TTS for segment-based audio mixing in radio dramas. The workflow generates voice segments individually, then uses automated mixing tools to combine voices and SFX into a final audio file.
Frontmatter metadata drives radio drama script automation by defining character voices and segment parameters directly within the script format. This allows the workflow to automatically parse instructions and apply the correct TTS and SFX assets.
Running an automated radio drama mixing pipeline requires dependencies like numpy and soundfile for audio processing, pedalboard for mixing effects, and ffmpeg with ffprobe for media handling and final MP3 export.
venetanjiGenerate images and videos by invoking ComfyUI workflows via REST API.
bibo1243Convert text to MP3 speech using macOS say and ffmpeg.
wlzhConvert speech to different voices using RVC or Pedalboard processing.
curiositechGenerate speech with ElevenLabs and process audio to broadcast loudness standards.
