SKILL.md

---
name: coqui-tts-local-server
description: Ultra-low latency Coqui-TTS local server skill. Optimized for Paul Bettany (Jarvis) and HAL9000 voices.
version: 1.0.2
author: Hugo Espuny (@fakehec)
metadata:
  {
    "openclaw":
      {
        "emoji": "🔊",
        "requires": { "bins": ["curl", "bash"] },
        "tags": ["audio", "tts", "local", "coqui"]
      }
  }
---

# Coqui TTS local server

High-performance Text-to-Speech skill using a local Coqui-TTS server.

## Repository
[https://github.com/fakehec/coqui-tts-local-server](https://github.com/fakehec/coqui-tts-local-server)

## Server Configuration
This skill connects to a local server at `http://localhost:5100` (OpenAI-compatible API).

## Available Voices

- **JARVIS**: Calm, technical voice based on Paul Bettany's clone. (Default)
- **HAL**: Retro-tech voice inspired by HAL9000.

## Usage

```bash
{baseDir}/scripts/say.sh "Hello sir, the analysis is complete." --voice JARVIS --lang en
```

## Performance
- **Latency:** ~250ms for typical agent responses.
- **Hardware:** Optimized for NVIDIA GPU acceleration.