What is the [VOICE] tag used for?

The [VOICE] tag is a specialized marker placed at the end of a response containing a summary of 140 characters or less, which the CVI system reads aloud to confirm task completion.

What is English Practice Mode?

This mode helps non-native speakers by detecting non-ASCII input, providing the English equivalent, and requiring the user to repeat the command in English before execution.

Can I adjust the speed of the voice notifications?

Yes, use the `/cvi:speed` command to adjust the words per minute (WPM) to make the notifications faster or slower.

What happens if a response doesn't have a [VOICE] tag?

If no [VOICE] tag is present, the skill uses a fallback behavior where the first 200 characters of Claude's response are automatically read aloud.

How do I change the speech language?

You can set the output language using the `/cvi:lang` command or by manually editing the VOICE_LANG setting in your ~/.cvi/config file.

Voice Integration for Claude Code

Name: Voice Integration for Claude Code
Author: signalcompose

bysignalcompose

•

Productivity & Workflow

Enhances Claude Code with automated text-to-speech notifications and customizable voice summaries for task completions.

About

The Voice Integration (CVI) skill streamlines the developer workflow by providing real-time audio feedback and status updates directly within the Claude Code environment. It automates the creation of concise voice-synthesized summaries for every completed task, allowing developers to maintain awareness of progress without constantly monitoring the terminal. With support for multiple languages, adjustable speech rates, and a specialized English practice mode for non-native speakers, this skill transforms the CLI experience into a more interactive and accessible development process.

Key Features

Multi-language support for English and Japanese synthesized speech
Automated [VOICE] tag generation for concise task summaries
Interactive English practice mode for non-native speaker training
2 GitHub stars
Customizable TTS settings including speech rate and voice selection
Smart fallback behavior that reads response headers when tags are missing

Use Cases

Accessibility enhancement for developers requiring auditory confirmation of terminal actions
Hands-free progress monitoring while running long test suites or complex refactors
Improving technical English proficiency through interactive command repetition

About

Key Features

Multi-language support for English and Japanese synthesized speech
Automated [VOICE] tag generation for concise task summaries
Interactive English practice mode for non-native speaker training
2 GitHub stars
Customizable TTS settings including speech rate and voice selection
Smart fallback behavior that reads response headers when tags are missing

Use Cases

Accessibility enhancement for developers requiring auditory confirmation of terminal actions
Hands-free progress monitoring while running long test suites or complex refactors
Improving technical English proficiency through interactive command repetition