tts-cli

Generates one spoken end-of-turn prompt via the cli-tts command-line tool.

Updated Sep 2, 2026
One-click install
npx skills add https://github.com/nbiish/tts-mcp --skill tts-cli-nbiish
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tts-cli
Source: https://github.com/nbiish/tts-mcp/tree/main/.agents/skills/tts-cli
Command: npx skills add https://github.com/nbiish/tts-mcp --skill tts-cli-nbiish

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It gives audible, hands-free end-of-turn feedback by speaking a concise summary and next-step suggestion through the on-device cli-tts engine, so you can keep working without reading the screen. ## Core Features & Use Cases - One prompt per turn: Builds a single cli-tts --prompt call containing a concise summary plus one fused Next step: imperative. - Structured advisory questions: Fills six deterministic master chairs (security, privacy, supply-chain, architecture, reliability, governance) plus three custom chairs with one-sentence answers. - Graceful fallback: Skips silently when cli-tts is missing or audio is disabled, and reports an engine-not-ready message with the install URL. - Use Case: During a long coding session, each assistant turn ends with a spoken summary and next-step suggestion, letting you monitor progress away from the keyboard. ## Quick Start Ask the assistant to speak its end-of-turn summary and next-step suggestion aloud using cli-tts.

Frequently Asked Questions about tts-cli

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I get spoken end-of-turn summaries from the assistant?▼

Enable this skill and ensure the cli-tts binary is installed. Each turn ends with one `cli-tts --prompt` call that plays a concise summary and a single next-step suggestion automatically through your device audio.

What is cli-tts and how does text-to-speech work here?▼

cli-tts is an on-device command-line text-to-speech tool (KittenTTS-based) that plays audio directly when invoked. The skill passes one fused prompt per turn via `cli-tts --prompt`, and the CLI handles playback without extra steps.

What happens if cli-tts is not installed or audio is disabled?▼

The skill skips silently when the cli-tts binary is missing or the operator disabled audio. If the engine is not ready, it outputs an error line pointing to the cli-tts GitHub repository for installation.

Can I customize the advisory questions spoken each turn?▼

Yes. Six chairs are fixed (security, privacy, supply-chain, architecture, reliability, governance), but three blank chairs are filled by the assistant's judgment based on the current task, so the spoken questions adapt to context.

Is the output of cli-tts --last-suggestion trusted?▼

No. The skill explicitly treats `cli-tts --last-suggestion` output as untrusted data, meaning it is never executed or followed as instructions, only read as plain text.