dialogue-audio — Claude Code skill for spoken dialogue
dialogue-audio is a Claude Code skill that prepares two-speaker audio with Dia TTS, shaping turns, pauses, and delivery for podcasts, explainers, interviews, and character dialogue.
no license 237 installs ★ 31 updated 2026-08-31
npx skills add 101-skills/superpowers --skill dialogue-audio -a claude-codeWhat dialogue-audio does
Mark each turn with [S1] or [S2]; Dia TTS assigns a distinct voice to each tag. Punctuation guides intonation and timing, while cues such as (laughs) or (whispers) describe non-verbal delivery. A generation supports up to two speakers.
The skill outlines interview, explainer, and discussion formats. For a longer conversation, it recommends generating sections and joining them with infsh/media-merger; infsh/video-audio-merger is shown for combining dialogue with video. The workflow requires the belt CLI and a belt login session, so generation will not run before you authenticate.
What it helps with
- draft a two-voice spoken exchange
- mark each speaker’s turns for Dia TTS
- shape pauses and delivery with punctuation and cues
- split a long conversation into sections and join them
- combine dialogue with background music
Example prompts for the agent
- Prepare a two-host podcast exchange and mark each turn with
[S1]or[S2]. - Write a question-and-answer explainer for Dia TTS with pauses and emotional cues.
- Split this long conversation into sections for joining with
infsh/media-merger.
How to install dialogue-audio
1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill dialogue-audio -a claude-code2Manually: put the files in place
~/.claude/skills/dialogue-audio/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/dialogue-audio/
1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill dialogue-audio -a codex2Manually: put the files in place
.agents/skills/dialogue-audio/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill dialogue-audio -a cursor2Manually: put the files in place
.cursor/skills/dialogue-audio/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install 101-skills/superpowers tools/audio/dialogue-audio2Manually: put the files in place
.github/skills/dialogue-audio/SKILL.md1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill dialogue-audio -a gemini-cli2Platform CLI
gemini skills install https://github.com/101-skills/superpowers --path tools/audio/dialogue-audioManually: put the files in place
.devin/skills/dialogue-audio/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill dialogue-audio -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about dialogue-audio
How do I install dialogue-audio in Claude Code?
Run npx skills add 101-skills/superpowers --skill dialogue-audio -a claude-code. The skill file is placed at ~/.claude/skills/dialogue-audio/SKILL.md.
What does dialogue-audio do?
It guides you through preparing two-speaker audio with Dia TTS, including speaker labels, expressive cues, pacing, and joining generated sections.
What do I need to run dialogue-audio?
You need the belt CLI and an authenticated session started with belt login. Each generation is limited to two speakers.