A versatile multimodal AI assistant powered by Google Gemini, offering high-speed text and voice interaction capabilities.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gemini-assistant
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 gemini-assistant 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 Gemini Assistant?
The Gemini Assistant is a sophisticated integration designed to bring the power of Google's latest generative models to your local environment. By utilizing the Gemini Flash architecture, it provides near-instantaneous responses for both text-based queries and complex audio interactions. This skill is a core component for developers looking to build interactive agents within the Openclaw Skills ecosystem, offering a bridge between standard CLI inputs and advanced AI reasoning.
Built with extensibility in mind, it allows users to switch between various model versions, including experimental audio-preview releases. Whether you are automating documentation lookups or creating a voice-activated terminal assistant, this tool provides the necessary infrastructure to handle multimodal data streams efficiently.
Gemini Assistant Use Cases
- Ask complex technical questions and receive structured text responses.
- Process audio files to generate transcripts or intelligent voice replies.
- Integrate high-speed AI reasoning into local terminal workflows.
- Build voice-first interactive agents for hands-free system management.
How Gemini Assistant Works
- The user initiates a request via the command line or an agent interface, passing either a string or an audio file path.
- The skill handler authenticates with the Google Gemini API using a secure API key stored in environment variables.
- The input is processed by the configured Gemini model, such as the flash-native-audio-preview for optimized audio handling.
- The assistant generates a multimodal response consisting of text and, optionally, a voice file path.
- The output is returned as a structured JSON object, allowing for easy parsing by other tools in the Openclaw Skills framework.
Gemini Assistant Setup
To get started with Gemini Assistant, ensure you have the necessary dependencies installed:
pip install google-genai numpy soundfile librosa
You must also have FFmpeg installed on your system for audio conversion tasks. Configure your API access by setting your key:
export GEMINI_API_KEY="your-api-key-here"
Alternatively, you can create a .env file within the skill directory. Run the skill to verify the installation:
python3 handler.py "Hello world"
Gemini Assistant Data Schema & Taxonomy
The Gemini Assistant skill utilizes a clear JSON structure for its output to ensure compatibility with various automation agents.
| Attribute | Description |
|---|---|
message |
A string containing the internal media pointer (e.g., [[audio_as_voice]]) and the temporary path to the generated OGG audio file. |
text |
The primary text-based response from the Gemini model. |
model |
The specific model ID used for the transaction, configurable within the handler.py file. |
Gemini Assistant Advanced Features
- Support for native audio input/output, bypassing the need for separate TTS/STT engines.
- Configurable model parameters to prioritize either cost-efficiency or advanced reasoning.
- Extensible system instructions to define custom personas or restricted behavioral guidelines.
- Seamless integration into larger multi-agent systems powered by Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Sentinel Security Monitor
Sentinel transforms any Android device running IP Webcam into a sovereign, frugal motion detection system integrated with AI agents.
Web Search (Perplexity)
A high-performance search and content retrieval skill for AI agents powered by the Perplexity API and local markdown extraction.
Claude Usage Checker
An automated utility for checking Claude Code and Claude Max usage quotas and reset schedules via the CLI.
AppStore Rating Pulse
An automated monitoring tool for tracking iOS App Store ratings across multiple countries without requiring an API key.
Gemini Voice Assistant
A voice-to-voice AI assistant leveraging the Gemini Live API for natural, real-time spoken interactions.
usewhisper-autohook
An automated memory management tool for OpenClaw agents that handles context retrieval and conversation ingestion via Whisper Context.
Featured*
