Local TTS — Claude Code Plugin

Free, offline text-to-speech for Claude Code. Powered by VoxCPM2 (2B params, Apache-2.0).

30 languages. Voice design. Voice cloning. Zero API calls. Zero cost.

https://github.com/vdk888/local-tts/raw/main/demo.mp4

Every voice in this demo was generated by Local TTS — including the narrator's.

Features

Feature	Description
Text-to-Speech	Convert any text to natural speech in 30 languages
Voice Design	Describe a voice in natural language and generate it — no samples needed
Voice Cloning	Clone any voice from a 3-10 second reference clip
Offline	Runs 100% locally on your machine. No API keys, no cloud, no cost
Apple Silicon	Optimized for Metal (MPS) on M-series Macs

Installation

As a Claude Code Plugin (recommended)

# Add the marketplace
/plugin marketplace add vdk888/local-tts

# Install the plugin
/plugin install local-tts@local-tts-marketplace

Setup

On first use, run the setup to create the Python environment:

/local-tts:local-tts

Claude will automatically run the setup script if the environment isn't configured yet. Or run it manually:

bash ~/.claude/plugins/cache/local-tts-marketplace/local-tts/1.0.0/scripts/setup.sh

Requirements:

• Python 3.10+
• macOS with Apple Silicon (recommended) or Linux with CUDA
• ~10 GB disk space for model weights (downloaded on first use)

Usage

Once installed, just ask Claude naturally:

• "Say hello in French"
• "Read this paragraph out loud"
• "Clone my voice from this file and say..."
• "Generate a voiceover with a warm female voice"

Or invoke the skill directly:

/local-tts:local-tts

Voice Design

Describe any voice — no reference audio needed:

"Say 'Welcome to our podcast' with a warm, calm female voice, mid-30s, American accent"

"Generate a voiceover with an older British man, deep voice, slow and authoritative"

Voice Cloning

Provide a short audio clip (3-10 seconds) and clone the voice:

"Clone the voice in ~/voice-sample.mp3 and say 'This is a test'"

You can combine cloning with style guidance:

"Clone ~/sample.mp3 but make it sound more enthusiastic and happy"

Supported Languages

Arabic, Burmese, Chinese (+ dialects), Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Indonesian, Italian, Japanese, Khmer, Korean, Lao, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Tagalog, Thai, Turkish, Vietnamese.

No language configuration needed — just write your text in any supported language.

Performance

Metric	Value
Model load	~25s (cached weights)
Generation speed	RTF ~2.3x (10s audio in ~23s)
First-time setup	~2 min (venv) + ~5 min (model download)
Model size	~10 GB
Output format	48 kHz WAV

How It Works

This plugin wraps VoxCPM2 by OpenBMB — a 2-billion parameter text-to-speech model supporting 30 languages with voice design and cloning capabilities. The model runs locally via PyTorch on Apple Silicon (Metal/MPS) or CUDA GPUs.

Configuration

Environment variables for customization:

Variable	Default	Description
LOCAL_TTS_VENV	~/.local-tts/venv	Python venv location
LOCAL_TTS_PYTHON	python3	Python binary for venv creation

License

Apache-2.0 — free for personal and commercial use.

Credits

• VoxCPM2 by OpenBMB — the TTS model
• Bubble Invest — plugin packaging and distribution

---

Built by Bubble Invest with Claude Code.