voice-output

Name: voice-output
Availability: InStock
Author: winsorllc

Convert text into audible speech via system TTS or Web Speech API.

1|Updated Feb 25, 2026

Search Tags:#voice #audio #tts #notification #speech #speak

Ready to run

npx skills add https://github.com/winsorllc/upgraded-carnival --skill voice-output

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: voice-output
Source: https://github.com/winsorllc/upgraded-carnival/tree/main/.pi/skills/voice-output
Command: npx skills add https://github.com/winsorllc/upgraded-carnival --skill voice-output

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill allows for text-to-speech functionality, enabling audio output for notifications, announcements, or accessibility needs.

Core Features & Use Cases

System TTS: Utilizes native OS commands (say on macOS, espeak on Linux) for quick audio feedback.
Browser TTS: Leverages the Web Speech API via Chrome DevTools Protocol for in-browser speech.
Use Case: Announce the completion of a long-running job with a spoken summary of the results, or read out important notifications to the user.

Quick Start

Use the voice-output skill to speak the phrase "Hello, world!" aloud.

Frequently Asked Questions about voice-output

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

FAQPage Schema

How do I convert text to speech for audio notifications?▼

To convert text to speech for audio notifications, this Skill uses system-level TTS engines like `say` or `espeak`, or the browser-based Web Speech API, to output audible spoken content. It supports job completion announcements and user-requested spoken text.

Does text-to-speech output work with browser TTS APIs?▼

Yes, browser TTS is supported by leveraging the Web Speech API via Chrome DevTools Protocol. This requires a running Chrome instance with CDP enabled to generate audible speech directly within the browser environment.

What system commands do I need for native speech synthesis?▼

For native speech synthesis, you need access to system commands like `say` on macOS or `espeak` on Linux. These native OS commands allow the Skill to generate quick audio feedback without relying on a browser.

When should I use system TTS versus browser TTS for spoken output?▼

Use system TTS via `say` or `espeak` for quick, native OS-level audio feedback. Use browser TTS via the Web Speech API when your workflow operates within a Chrome instance and requires in-browser speech generation.

Can I announce the completion of a long-running job with spoken audio?▼

Yes, you can announce the completion of a long-running job with spoken audio. The Skill converts text summaries into audible speech, enabling audio notifications and accessibility alerts for important job results.