@jay-zod/speak

Convert text to speech using Chatterbox TTS on Apple Silicon

Package details

← Back
skill

Install @jay-zod/speak from npm and Pi will load the resources declared by the package manifest.

npm repohome report
$ pi install npm:@jay-zod/speak
Package
@jay-zod/speak
Version
1.1.0
Published
Jan 27, 2026
Downloads
16/mo · 6/wk
Author
jay-zod
License
MIT
Types
skill
Size
6.5 MB
Dependencies
6 dependencies · 1 peer
Pi manifest JSON
{
  "skills": [
    "SKILL.md"
  ]
}

Security note

Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.

README

A fast CLI tool for AI agents to convert their text output to speech using Chatterbox TTS on Apple Silicon.

Quick Start

git clone https://github.com/EmZod/speak.git
cd speak
bun install

# First run auto-installs Python dependencies
bun run src/index.ts "Hello, world!" --play

Create an alias for easier access:

alias speak="bun run $(pwd)/src/index.ts"

Requirements

  • macOS with Apple Silicon (M Series)
  • Bun
  • Python 3.10+
  • sox (for long documents): brew install sox

Basic Usage

speak "Hello, world!" --play        # Generate and play
speak article.md --stream           # Stream long content
speak --clipboard --play            # Read from clipboard
speak document.md --output out.wav  # Save to file

Key Features

# Long documents - auto-chunk for reliability
speak book.md --auto-chunk --output book.wav

# Resume interrupted generation
speak --resume manifest.json

# Batch processing
speak *.md --output-dir ~/Audio/

# Estimate duration before generating
speak --estimate document.md

# Concatenate audio files
speak concat part1.wav part2.wav --out combined.wav

Commands

Command Description
speak <text|file> Generate speech
speak health Check system status
speak models List available models
speak concat <files> Combine audio files
speak daemon kill Stop TTS server

Common Options

Option Description
--play Play after generation
--stream Stream as it generates
--output <path> Output file or directory
--auto-chunk Chunk long documents
--estimate Show duration estimate
--dry-run Preview without generating

Documentation

Development

bun install          # Install dependencies
bun test             # Run tests
bun run typecheck    # Type check

For AI Agents

Copy SKILL.md to your agent's skills directory:

cp SKILL.md ~/.claude/skills/speak-tts/SKILL.md

See AGENTS.md for setup details.

License

MIT