Can I adjust how fast Claude speaks?

Yes, you can customize the speech rate. We recommend 100-150 WPM for deep comprehension and 200-250 WPM for quickly scanning through text.

Is this skill compatible with premium macOS voices like Samantha?

Yes, it can access any voice available in your macOS System Settings, including premium, natural-sounding, and high-quality voice options.

How do I find voices for languages other than English?

You can use the 'say_list_voices' tool with a language filter (e.g., 'es' for Spanish or 'fr' for French) to see all compatible voices installed on your Mac.

What audio formats can I save speech to?

The skill supports saving audio output to both .aiff and .m4a file formats, making it easy to use the generated speech in other applications.

Does this skill require an internet connection or external API?

No, the Say Skill utilizes the native macOS 'say' command, meaning it works entirely offline and uses the voices already installed on your system.

Voice & Speech Synthesis

Name: Voice & Speech Synthesis
Author: nathanvale

bynathanvale

•

生产力与工作流

Integrates macOS native text-to-speech capabilities into Claude Code to provide auditory feedback and audio file generation.

关于

The Say Skill brings macOS's powerful 'say' command into the Claude Code environment, specifically designed to support developers who benefit from auditory processing and hyperfocus. By allowing Claude to speak text aloud, list available system voices, and export speech to high-quality audio files like .m4a, it creates an accessible, multi-modal workflow. This tool is particularly effective for developers using the SideQuest ecosystem to maintain focus, allowing them to 'hear' code or documentation without breaking their terminal-based concentration.

主要功能

Support for premium, natural-sounding system voices
Customizable speech rates for varied comprehension speeds
Speech-to-file export in .aiff and .m4a formats
Comprehensive voice library management and filtering
Native macOS text-to-speech integration
1 GitHub stars

使用场景

Generating quick voice-over assets for technical tutorials or demos
Enhancing accessibility and focus for neurodivergent developers through multi-modal feedback
Auditory debugging and reviewing long documentation blocks for better retention

关于

主要功能

Support for premium, natural-sounding system voices
Customizable speech rates for varied comprehension speeds
Speech-to-file export in .aiff and .m4a formats
Comprehensive voice library management and filtering
Native macOS text-to-speech integration
1 GitHub stars

使用场景

Generating quick voice-over assets for technical tutorials or demos
Enhancing accessibility and focus for neurodivergent developers through multi-modal feedback
Auditory debugging and reviewing long documentation blocks for better retention