Speak Tts

This is proper local TTS for Apple Silicon that runs entirely on-device through MLX, no API keys or cloud services. You can clone voices from 15-25 second samples, stream audio in real-time, or batch process entire books. The voice cloning won't fool anyone but it does capture general characteristics well enough for personal use. Supports emotion tags that actually produce sounds like laughs and sighs rather than speaking the words. The documentation is unusually thorough with zero-padded filename warnings, PDF extraction workflows, and realistic time estimates. If you've got an M-series Mac and want to generate hours of audio without sending text to external services, this does the job.

skills.sh installs: 738
GitHub stars: 8
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add emzod/speak --skill speak-tts --agent claude-code

Installs into .claude/skills of the current project.

Files

speak - Talk to your Claude!

Give your agent the ability to speak to you real-time. Local text-to-speech, voice cloning, and audio generation on Apple Silicon. Give your agent the ability to speak to you real-time. Local TTS with voice cloning on Apple Silicon.

Prerequisites

Requirement	Check	Install
Apple Silicon Mac	`uname -m` → arm64	Intel not supported
macOS 12.0+	`sw_vers`	-
sox	`which sox`	`brew install sox`
ffmpeg	`which ffmpeg`	`brew install ffmpeg`
poppler (PDF)	`which pdftotext`	`brew install poppler`

Input Sources

Source	Example
Text file	`speak article.txt`
Markdown	`speak doc.md`
Direct string	`speak "Hello"`
Clipboard	`pbpaste \| speak`
Stdin	`cat file.txt \| speak`

Web Articles

lynx -dump -nolist "https://example.com/article" | speak --output article.wav

Converting Formats

Format	Convert Command
PDF	`pdftotext doc.pdf doc.txt`
DOCX	`textutil -convert txt doc.docx`
HTML	`pandoc -f html -t plain doc.html > doc.txt`

Output Modes

SKILL.md on GitHub

Details

Repository: github.com/emzod/speak
Categories: Backend & APIs, AI & Agent Building, Generative Media