Dialogue Audio

This generates realistic two-speaker conversations using Dia TTS through the inference.sh CLI. You write dialogue with [S1] and [S2] speaker tags, and it assigns distinct voices automatically. The punctuation actually matters here—exclamation points add energy, ellipses create hesitation, parenthetical sounds like (laughs) work as expected. Good for podcast intros, explainer dialogues, or character conversations where you need natural back-and-forth without the complexity of ElevenLabs voice selection. The script writing tips are solid—write like people talk, not like they write, and break up monologues into actual exchanges.

skills.sh installs: 6.4K
GitHub stars: 173

View on GitHub

Install

$ npx -y skills add inferen-sh/skills --skill dialogue-audio --agent claude-code

Installs into .claude/skills of the current project.

Files

Install the belt CLI skill: npx skills add belt-sh/cli

Dialogue Audio

Create realistic multi-speaker dialogue with Dia TTS via inference.sh CLI.

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Two-speaker conversation
belt app run falai/dia-tts --input '{
  "prompt": "[S1] Have you tried the new feature yet? [S2] Not yet, but I heard it saves a ton of time. [S1] It really does. I cut my workflow in half. [S2] Okay, I am definitely trying it today."
}'