Delegate independent tasks to specialized agents working concurrently with isolated context.
Claude Speak
claude-speak
Speak text aloud using high-quality AI voice synthesis (Kokoro TTS on Apple Silicon). Use when user asks to vocalize, narrate, or speak text out loud.
SKILL.md
Full skill instructions
Claude Speak
Vocalize text using high-quality text-to-speech. British male voice (bm_george) by default.
When to Use
Invoke when user:
- Asks to "say this out loud" or "speak this"
- Wants narration or audio feedback
- Uses
/speakcommand - Requests vocalization of content
Core Command
~/Projects/claude-speak/.venv/bin/claude-speak-client "Text to speak"
That's it. The daemon runs in background via launchd - instant response.
TIP: For longer text, append & to run fire-and-forget (see "Long Text" section below).
Options
# Different voice
~/Projects/claude-speak/.venv/bin/claude-speak-client -v af_heart "Warm female voice"
# Adjust speed (default 1.0)
~/Projects/claude-speak/.venv/bin/claude-speak-client -s 1.2 "Speaking faster"
# Quiet mode (suppress errors)
~/Projects/claude-speak/.venv/bin/claude-speak-client -q "Silent on success"
# Custom timeout (default: 300s / 5 min)
~/Projects/claude-speak/.venv/bin/claude-speak-client -t 600 "Very long text..."
Long Text (3+ sentences)
For longer content, use fire-and-forget mode with shell backgrounding:
~/Projects/claude-speak/.venv/bin/claude-speak-client "Your longer text here..." &
The trailing & runs the command in the background at the shell level, so Claude Code doesn't track it as a task. The audio plays while the conversation continues—no timeout errors or false "failed" notifications.
Why this works: Claude Code's run_in_background still monitors the task and may report timeout failures even when audio completes successfully. Shell backgrounding (&) avoids this entirely.
Available Voices
| Voice | Description |
|---|---|
bm_george | British male, distinguished (DEFAULT) |
af_heart | American female, warm |
am_adam | American male, deep |
bf_emma | British female, elegant |
Troubleshooting
If "Daemon not running" error:
~/Projects/claude-speak/.venv/bin/claude-speak-daemon start
Best Practices
- For short text (1-2 sentences): run normally
- For longer text (paragraphs): use
&fire-and-forget - Check daemon status if issues arise
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
