Installation

Open Claude Code and run this command:

/plugin install local-tts@claude-code-plugins-plus

Use --global to install for all projects, or --project for current project only.

What It Does

Generate speech locally with VoxCPM2. 30 languages, voice design, voice cloning. Zero cloud, zero cost.

Runs 100% on your machine using VoxCPM2 (2B-parameter model, Apache-2.0). Optimized for Apple Silicon via Metal (MPS). No API keys, no rate limits, no telemetry.

Features

Feature	Description
Text-to-Speech	30 languages, auto-detected from input text
Voice Design	Describe a voice in natural language (e.g. "warm female voice, mid-30s")
Voice Cloning	Clone any voice from a 3-10 second reference clip
Ultimate Cloning	Reference + prompt for maximum fidelity (vocal micro-nuances)
48 kHz output	Production-quality WAV ready for Telegram, video, podcast

Skills (1)

local-tts SKILL.md View full skill →

Generate speech locally from text using VoxCPM2 (2B params, Apache-2.

ReadBash(python3:*)Bash(file:*)Bash(ls:*)

Local TTS — Offline Text-to-Speech

Generate speech from text using VoxCPM2 locally. 30 languages, voice design, voice cloning. Runs on Apple Silicon via Metal. Apache-2.0, zero cost.

Overview

This skill wraps VoxCPM2 (OpenBMB, Apache-2.0) for local text-to-speech. It supports three modes:

Default voice — just feed text, get natural speech in 30 languages (auto-detected)
Voice Design — describe the voice in a parenthetical prefix, get matching speech
Voice Cloning — provide a 3-10s reference clip, the output mimics the voice

All processing happens on-device. No API keys. No network calls after the initial model download. Output is 48 kHz WAV ready for any use (Telegram voice messages, podcasts, video narration).

Prerequisites

Python 3.10+ (3.12 recommended)
macOS with Apple Silicon preferred (M1/M2/M3/M4). Linux with CUDA also works.
~10 GB disk space for model weights (downloaded once on first use)
~16 GB RAM recommended

The skill expects a Python venv at ~/.local-tts/venv with the voxcpm package installed. If missing, create it:


mkdir -p ~/.local-tts
python3.12 -m venv ~/.local-tts/venv
~/.local-tts/venv/bin/pip install --upgrade pip voxcpm

First generation downloads ~10 GB of model weights to ~/.cache/huggingface/. Subsequent runs load the cache in ~30s.

Instructions

Step 1 — Verify the environment


ls ~/.local-tts/venv/bin/python && echo "venv OK" || echo "Run setup first"

If the venv is missing, guide the user through the setup commands above.

Step 2 — Generate the speech

Use the generate.py script bundled in this plugin. The entry point:


VENV=~/.local-tts/venv
SCRIPT=${CLAUDE_PLUGIN_ROOT}/scripts/generate.py
OUT=/tmp/tts_$(date +%s).wav

Default voice (auto-detected language):


"$VENV/bin/python" "$SCRIPT" --text "Your text here." --out "$OUT"

Voice Design — describe the voice in parentheses at the start. The parenthetical is stripped from the spoken audio.


"$VENV/bin/python" "$SCRIPT" \
  --text "(warm female voice, mid-30s, American accent)Welcome back." \
  --out "$OUT"

Description examples that work:

(young woman, gentle and sweet voice)
(older man, deep resonant voice, slow pace)
(cheerful, energetic, fast-talking)
(voix féminine chaleureuse, ton posé) — descriptions in any supported language

How It Works

Via natural language (auto-triggered)

Just ask Claude to:

"Say hello in French"
"Generate a voiceover for this text: ..."
"Clone this voice: /path/to/sample.wav and say ..."
"Make a warm female voice reading: ..."

Direct invocation


VENV=~/.local-tts/venv
SCRIPT=${CLAUDE_PLUGIN_ROOT}/scripts/generate.py

"$VENV/bin/python" "$SCRIPT" --text "Hello world" --out /tmp/hello.wav

"$VENV/bin/python" "$SCRIPT" \
  --text "(warm female voice, mid-30s, calm)Welcome back." \
  --out /tmp/design.wav

"$VENV/bin/python" "$SCRIPT" \
  --text "This is my cloned voice." \
  --ref /path/to/sample.wav \
  --out /tmp/clone.wav

cat article.txt | "$VENV/bin/python" "$SCRIPT" --stdin --out /tmp/article.wav

Supported languages (30)

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 tag needed — VoxCPM auto-detects from the text.

FAQ

**`ModuleNotFoundError: voxcpm`** — venv missing or wrong path. Run the setup commands above.

local-tts

Installation

What It Does

Features

Skills (1)

Local TTS — Offline Text-to-Speech

Overview

Prerequisites

Instructions

Step 1 — Verify the environment

Step 2 — Generate the speech

How It Works

Via natural language (auto-triggered)

Direct invocation

Supported languages (30)

FAQ

Ready to use local-tts?

Related Plugins

local-tts

Installation

What It Does

Features

Skills (1)

Local TTS — Offline Text-to-Speech

Overview

Prerequisites

Instructions

Step 1 — Verify the environment

Step 2 — Generate the speech

How It Works

Via natural language (auto-triggered)

Direct invocation

Supported languages (30)

FAQ

Ready to use local-tts?

Related Plugins

ai-ethics-validator

ai-sdk-agents

anomaly-detection-system

automl-pipeline-builder

classification-model-builder

clustering-algorithm-runner