A retro robotic text-to-speech engine for AI agents that recreates the iconic Commodore 64 SAM voice.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install sam-tts
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install sam-tts using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is sam-tts?
The sam-tts skill brings the classic Software Automatic Mouth (SAM) synthesizer to modern AI agents, enabling them to communicate using the distinct, 8-bit robotic voice made famous on the Commodore 64. By integrating this engine, developers can give their agents a unique auditory personality that stands out from standard, modern neural voices.
As a versatile component of Openclaw Skills, this tool handles everything from one-off voice commands to a persistent speech mode where every agent response is automatically synthesized. It is built on Node.js and provides deep customization through pitch, speed, and phonetic controls, making it ideal for creative projects, nostalgic interfaces, or distinctive notification systems.
sam-tts Use Cases
- Creating unique vocal identities for AI assistants in Discord, Telegram, or WhatsApp.
- Generating retro-themed audio assets for game development and interactive media.
- Providing hands-free auditory feedback for developers monitoring long-running CLI tasks.
- Enhancing accessibility with a lightweight, low-resource speech synthesis alternative.
How sam-tts Works
- The user triggers the skill via a direct command like /sam or by enabling the global SAM mode toggle.
- The skill references the memory/sam-mode.json file to retrieve current voice parameters including pitch, speed, mouth, and throat settings.
- The text input is passed to a Node.js wrapper script which interfaces with the SAM synthesis engine.
- The engine generates a PCM WAV file (22050 Hz, 8-bit, Mono) containing the synthesized speech.
- The agent delivers the audio file to the user, optionally converting the format if the target platform requires specific codecs like OPUS or MP3.
sam-tts Setup
To get started with this skill, ensure you have Node.js 18+ installed. Follow these steps to prepare your environment:
# Navigate to the skill directory
cd sam-tts
# Install the necessary sam-js dependencies
npm install
Once installed, you can verify the setup by running a test synthesis using the provided wrapper script in your terminal.
sam-tts Data Schema & Taxonomy
The skill manages its configuration and state using a localized JSON file to ensure persistence across sessions within the Openclaw Skills ecosystem.
State Configuration (memory/sam-mode.json)
| Parameter | Type | Default | Description |
|---|---|---|---|
| enabled | boolean | false | Toggles if all agent responses use TTS. |
| pitch | integer | 64 | Sets the vocal frequency range (0-255). |
| speed | integer | 72 | Controls the rate of speech (1-255). |
| mouth | integer | 128 | Adjusts the simulated mouth resonance (0-255). |
| throat | integer | 128 | Adjusts the simulated throat timbre (0-255). |
sam-tts Advanced Features
- Phonetic Input Mode: Use specific phoneme codes and stress markers (1-8) for perfect pronunciation of non-standard words.
- Platform-Aware Conversion: Logic to request ffmpeg installation for automatic OGG/OPUS or MP3 transcoding based on the chat client.
- Persistent Voice Profiles: Save and swap custom voice parameters by modifying the underlying memory schema.
- Headless Automation: Use the scripts/sam-tts-wrapper.js directly in automated pipelines to generate JSON metadata alongside audio output.
SKILL.md
Loading
Related Openclaw Skills
Krea.ai Image Generation Skill
A professional-grade AI skill for generating high-quality images via Krea.ai using advanced models like Flux and Imagen.
FOSMVVM ViewModel Test Generator
A specialized generator for creating Swift ViewModel tests that validate data integrity, versioning, and multi-locale localization.
FOSMVVM ViewModel Generator
Automate the creation of type-safe, localized ViewModels and factories for SwiftUI using the FOSMVVM architecture.
FOSMVVM UI Tests Generator
Automates the creation of robust UI tests for FOSMVVM SwiftUI views using XCTest and the FOSTestingUI framework.
Telegram Context
A toggle-enabled skill that retrieves recent Telegram message history to ensure conversational continuity across agent sessions.
X-Claw Agent
A secure Python-based runtime for executing crypto wallet operations, automated trading, and liquidity management with a fail-closed deterministic architecture.
Featured*
