home / skills / pchalasani / claude-code-tools / voice-update

voice-update skill

safe

This skill delivers a concise spoken update of what was accomplished, helping users stay informed with quick audio summaries.

npx playbooks add skill pchalasani/claude-code-tools --skill voice-update

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

1.7 KB

---
name: voice-update
description: This skill should be used when the agent needs to give a spoken voice update to the user, or when reminded by a Stop hook to provide audio feedback. Use this skill to speak a short summary of what was accomplished.
---

# Voice Update Skill

Provide spoken audio feedback to the user using pocket-tts.

## When to Use

- When finishing a task and a Stop hook reminds to give voice feedback
- When the user explicitly asks for a spoken summary
- When providing important status updates that benefit from audio

## How to Use

1. Summarize what was accomplished in 1-2 short, conversational sentences
2. Call the `say` script with the summary text

## Calling the Say Script

Use Bash to call the say script:

```bash
${CLAUDE_PLUGIN_ROOT}/scripts/say "Your summary here"
```

Example:
```bash
${CLAUDE_PLUGIN_ROOT}/scripts/say "I've fixed the bug in the login handler and added the unit tests."
```

With a specific voice:
```bash
${CLAUDE_PLUGIN_ROOT}/scripts/say --voice azure "Task completed successfully."
```

## Summary Guidelines

- Keep it to 1-2 sentences maximum
- Be conversational, not robotic
- Match the user's communication style - if they're casual or use colorful language, mirror that tone
- Focus on what was accomplished, not technical details
- Avoid code snippets, file paths, or technical jargon
- Examples:
  - "I've updated the configuration file and restarted the server."
  - "The tests are now passing. I fixed three type errors."
  - "Done! I created the new component and added it to the main page."

## Notes

- The say script auto-starts the pocket-tts server if not running (first use may take ~30-60s)
- Requires `uvx` and `afplay` (macOS) or `aplay` (Linux)

Overview

This skill provides a quick spoken voice update to users using the pocket-tts-based say script. It’s designed for short, conversational summaries of what the agent accomplished or important status changes. Use it whenever audio feedback improves clarity or confirms completion.

How this skill works

Compose a 1–2 sentence conversational summary of the outcome you want to communicate. Call the bundled say script to send that text to pocket-tts; the script will auto-start the server if needed and play audio via the system audio tool. Optional flags let you select a voice variant when desired.

When to use it

After finishing a task when a Stop hook requests audio feedback
When the user explicitly asks for a spoken summary or confirmation
For brief audible status updates during long-running workflows
When hands-free or attention-grabbing feedback is helpful
To confirm high-level outcomes to non-technical stakeholders

Best practices

Keep the update to 1–2 short sentences focused on outcomes, not implementation details
Match the user’s tone—be casual if they are casual, professional if they expect formality
Avoid code, file paths, and technical jargon in the spoken text
Use the --voice option only when a distinct voice helps clarity or accessibility
Remember first use may take 30–60s while pocket-tts starts; indicate potential delay if relevant

Example use cases

"I've updated the configuration and restarted the service." after deploying a change
Announcing test results: "The test suite is green; I fixed three type errors."
Confirming task completion in a hands-free environment: "Done! I created the new component and merged it."
Providing audible alerts for long operations: "Backup complete. All files uploaded."
Giving stakeholders a non-technical summary after a code refactor: "Refactor finished—performance improved and no API changes."

FAQ

How do I invoke the voice update from a script?

Call the say script: ${CLAUDE_PLUGIN_ROOT}/scripts/say "Your short summary here". Add --voice <name> to pick a voice.

What dependencies are required?

Pocket-tts is used by the say script. The script requires uvx and a system audio player (afplay on macOS or aplay on Linux). The script auto-starts the pocket-tts server on first use.