A powerful API bridge for controlling Amazon Alexa and Echo devices through Text-to-Speech, media playback, and routine triggers.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install voicemonkey
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 voicemonkey 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 VoiceMonkey?
VoiceMonkey is a robust skill designed for developers looking to integrate Amazon Alexa capabilities into their automated workflows. By utilizing the VoiceMonkey API v2, this Openclaw Skills integration allows users to send TTS announcements, play high-quality audio or video on Echo Show devices, and even trigger complex Alexa routines programmatically. It serves as a critical link between external applications and the Alexa ecosystem, providing a seamless way to broadcast notifications or manage smart home environments without manual intervention.
Whether you are building a custom monitoring dashboard or an automated home notification system, this skill provides the necessary endpoints to interact with Echo devices. By leveraging Openclaw Skills, developers can easily include voice-based feedback into their CLI tools and agentic workflows, making it easier than ever to bring physical presence to digital triggers.
VoiceMonkey Use Cases
- Send automated voice notifications for server alerts or CI/CD build status.
- Trigger smart home routines (e.g., turning on lights) based on external API events.
- Display live security camera feeds or static images on Echo Show devices.
- Broadcast "Dinner is ready" or other household announcements directly from a terminal or script.
- Open specific websites or dashboards on Alexa-enabled screens automatically during certain triggers.
How VoiceMonkey Works
- The user authenticates by providing a VoiceMonkey API token and a target Device ID through the Openclaw Skills environment.
- A request is sent to the VoiceMonkey API v2 endpoints, such as /announcement, /trigger, or /flows.
- The API validates the security token and routes the command to the specified Amazon Echo device associated with the user account.
- The Echo device performs the requested action, which can include speaking TTS, playing media files, or launching an Alexa routine.
- For Echo Show devices, the skill handles specific media rendering requirements for images, videos, and websites to ensure compatible playback.
VoiceMonkey Setup
- Obtain your secret token from the Voice Monkey Console under Settings > API Credentials.
- Configure your environment variable to allow Openclaw Skills to access the API:
export VOICEMONKEY_TOKEN="your-secret-token"
- Alternatively, add the configuration to your local clawdbot.json file:
{
"skills": {
"entries": {
"voicemonkey": {
"env": { "VOICEMONKEY_TOKEN": "your-secret-token" }
}
}
}
}
- Locate your Device IDs in the Voice Monkey Console under Settings > Devices to target specific Echo hardware.
VoiceMonkey Data Schema & Taxonomy
The skill utilizes a structured parameter set to interface with the VoiceMonkey API. Data is organized as follows:
| Parameter | Required | Description |
|---|---|---|
device |
Yes | The unique Device ID for the target Echo device. |
text |
No | TTS text to be spoken, supporting SSML for advanced speech control. |
image |
No | HTTPS URL for images (JPG/PNG) displayed on Echo Show devices. |
video |
No | HTTPS URL for MP4 videos to be played on Echo Show. |
audio |
No | HTTPS URL for MP3/WAV audio files for sound playback. |
flow |
No | Numeric Flow ID to start a Voice Monkey Flow. |
VoiceMonkey Advanced Features
- Support for SSML (Speech Synthesis Markup Language) to add emotion, pitch, and specific pronunciation to announcements via Openclaw Skills.
- Capability to update Voice Monkey variables dynamically using the
var-[name]parameter during API calls. - Advanced media control including video repeat counts, image scaling modes, and custom corner radius clipping for Echo Show.
- Background audio support to play ambient music or chimes behind TTS announcements.
- Integration with Alexa Routines to trigger complex IoT sequences from a single API trigger call.
SKILL.md
Loading
Related Openclaw Skills
CNY Rate Calculator
An automated tool for fetching live CNY exchange rates and calculating business-specific tiered pricing models based on the Prairie Grasslands formula.
EmailAgent
An intelligent email assistant that uses LangChain and OpenAI to draft and send emails with a mandatory human approval step.
Keyswap
A specialized utility designed to automate the rotation and update of Claude Max API tokens across multiple OpenClaw Anthropic profiles.
VibeVoice TTS
A high-performance, local text-to-speech engine optimized for Spanish voice synthesis and mobile messaging.
Dex Personal CRM
An AI-powered integration to manage Dex CRM contacts, interaction notes, and follow-up reminders directly through a conversational interface.
Copilot Money CLI
A professional command-line interface for querying Copilot Money personal finance data including balances, holdings, and asset allocation.
Featured*
