A voice-to-voice AI assistant leveraging the Gemini Live API for natural, real-time spoken interactions.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gemini-voice-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-voice-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 Voice Assistant?
Gemini Voice Assistant is a sophisticated utility designed for the Openclaw Skills ecosystem, enabling developers and users to interact with Google's Gemini models using natural language speech. By utilizing the Gemini Live API, this skill bridges the gap between text-based AI and conversational voice interfaces, making it a powerful addition to any suite of Openclaw Skills.
The skill is optimized for speed and fluidity, handling both complex audio input processing and high-quality voice synthesis. It allows for a more human-centric interaction model where users can speak directly to their AI agent and receive spoken responses in return, significantly enhancing the user experience of Openclaw Skills.
Gemini Voice Assistant Use Cases
- Hands-free interaction with AI agents during development or daily tasks.
- Building voice-enabled automation workflows within the Openclaw Skills framework.
- Real-time spoken information retrieval for multitasking environments.
- Developing accessibility-focused tools that prioritize auditory feedback over traditional text interfaces.
How Gemini Voice Assistant Works
- The user initiates a request by providing either a text prompt or a path to an audio file (e.g., .ogg) to the skill handler.
- The skill authenticates with the Google Generative AI platform using a configured Gemini API key.
- If audio is provided, the skill uses specialized libraries like librosa and soundfile to prepare the data for the Gemini Live API.
- The Gemini model processes the input and generates a multimodal response containing both a text transcript and native audio data.
- The skill saves the generated audio to a temporary directory and returns a structured JSON object to the agent, facilitating a seamless flow within Openclaw Skills.
Gemini Voice Assistant Setup
To integrate this into your environment of Openclaw Skills, ensure you have the necessary dependencies and configuration in place.
First, install the required Python libraries:
pip install google-genai numpy soundfile librosa
You must also have FFmpeg installed on your system for audio conversion. Next, set your API key as an environment variable:
export GEMINI_API_KEY="your-api-key-here"
To run the skill in voice mode, use the following command structure:
python3 handler.py --audio /path/to/your/audio.ogg "optional context prompt"
Gemini Voice Assistant Data Schema & Taxonomy
The Gemini Voice Assistant organizes its communication through a standardized JSON schema designed for compatibility with other Openclaw Skills.
| Property | Type | Description |
|---|---|---|
| message | string | A special formatted string containing the [[audio_as_voice]] tag and the file path to the generated audio. |
| text | string | The literal text transcription of the AI's spoken response. |
Generated audio files are typically stored in the system temporary directory (e.g., /tmp/gemini_voice_xxx.ogg) for immediate playback or further processing by the agent.
Gemini Voice Assistant Advanced Features
- Support for the latest Gemini 2.5 Flash models for ultra-low latency voice responses.
- Dual-mode functionality supporting both text-only and full voice-to-voice pipelines.
- Configurable system instructions to tailor the voice assistant's personality and domain expertise.
- Efficient audio handling optimized for the Openclaw Skills architecture.
SKILL.md
Loading
Related Openclaw Skills
Gemini Assistant
A versatile multimodal AI assistant powered by Google Gemini, offering high-speed text and voice interaction capabilities.
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.
usewhisper-autohook
An automated memory management tool for OpenClaw agents that handles context retrieval and conversation ingestion via Whisper Context.
Whisper Context
A context optimization and long-term memory skill that reduces LLM token usage via delta compression and intelligent caching.
Featured*
