A high-performance transcription utility that leverages Google's Gemini models to convert audio files into text with zero external dependencies.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gemini-stt
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-stt 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 Speech-to-Text?
The Gemini Speech-to-Text skill is a developer-centric utility designed to process audio transcription tasks using either the direct Gemini API or Google Cloud Vertex AI. By prioritizing the gemini-2.0-flash-lite model, this skill offers an optimal balance of speed and cost-effectiveness for real-time applications. It is built to integrate seamlessly into Openclaw Skills ecosystems, providing a reliable way to handle voice data without the overhead of heavy external libraries.
Designed for portability and ease of use, the skill utilizes Python's standard library to manage authentication, file encoding, and API communication. This makes it an ideal choice for developers looking to add robust speech-to-text capabilities to their AI agents or automation scripts while maintaining a minimal footprint.
Gemini Speech-to-Text Use Cases
- Automatically transcribing voice notes from messaging platforms like Telegram.
- Converting recorded meetings or interviews in .mp3 or .wav formats into searchable text.
- Processing inbound audio media within automated Clawdbot workflows.
- Generating transcripts for podcasts or video voiceovers using state-of-the-art LLMs.
- Enabling voice-command processing for custom CLI tools and Openclaw Skills.
How Gemini Speech-to-Text Works
- The skill reads the target audio file and converts it into a base64-encoded string compatible with Google's API requirements.
- It performs an automatic authentication check, looking for gcloud Application Default Credentials (ADC) first, followed by a local GEMINI_API_KEY environment variable.
- Depending on the detected credentials, the skill initiates a request to either the Vertex AI or the direct Gemini API endpoint.
- The encoded data is processed by the selected model (defaulting to the ultra-fast gemini-2.0-flash-lite) using a specialized transcription prompt.
- The resulting text is extracted from the API response and returned via stdout for use in further automation steps.
Gemini Speech-to-Text Setup
To deploy this skill within your Openclaw Skills environment, ensure you have Python 3.10+ and select an authentication method:
Vertex AI Setup (Recommended)
gcloud auth application-default login
gcloud config set project YOUR_PROJECT_ID
Direct API Setup Add your API key to your environment variables:
export GEMINI_API_KEY='your_secret_key_here'
The script requires no external pip dependencies and can be executed directly from the terminal.
Gemini Speech-to-Text Data Schema & Taxonomy
The skill handles audio data and metadata through a streamlined process without persistent storage requirements. Data organization follows this structure:
| Component | Details |
|---|---|
| Supported Formats | .ogg, .opus, .mp3, .wav, .m4a |
| MIME Handling | Automatic detection based on file extension |
| Auth Logic | Prefers ADC (Vertex) over API Key (Direct) |
| Default Model | gemini-2.0-flash-lite |
| Metadata Output | Plain text transcription string |
Gemini Speech-to-Text Advanced Features
- Multi-model support allowing users to switch between Flash, Pro, and Preview versions of Gemini for varied quality needs.
- Force-override capabilities to prioritize Vertex AI over standard API access for enterprise compliance.
- Zero-dependency architecture ensuring compatibility across different Linux and macOS distributions within Openclaw Skills setups.
- Automated regional configuration for Vertex AI to minimize latency during transcription tasks.
- Seamless integration hooks for Clawdbot inbound media directories.
SKILL.md
Loading
Related Openclaw Skills
GhostBot ACLM
An AI-powered hook system for Uniswap v4 that automates liquidity rebalancing and dynamic fee optimization.
GhostBot ACLM: Automated Concentrated Liquidity Manager
An AI-powered Uniswap v4 hook system that automates liquidity provision, rebalancing, and fee optimization on Ethereum Sepolia.
Resend Email Sender
A streamlined email integration for Openclaw Skills that enables sending professional text and HTML emails via the Resend API without managing SMTP servers.
Pollinations Image Generation Skill
A modular terminal-based tool for generating high-quality AI images through the Pollinations.ai API.
Local STT (Parakeet / Whisper)
A high-performance local speech-to-text utility utilizing Parakeet and Whisper backends for ultra-fast, offline audio transcription.
Local Whisper STT
A private, high-accuracy offline speech-to-text engine for the Openclaw Skills ecosystem.
METADATA
Featured*
