A robust CLI tool for transcribing audio files using state-of-the-art LLMs via the OpenRouter API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openrouter-transcribe
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 openrouter-transcribe 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 OpenRouter Audio Transcription?
This skill enables developers to leverage audio-capable Large Language Models (LLMs) such as Gemini 1.5 Flash and GPT-4o-audio-preview for high-fidelity transcription. By integrating with OpenRouter, users can swap between different providers and models seamlessly to optimize for cost or accuracy.
This utility is a core component of the Openclaw Skills ecosystem, designed for automation and high-performance audio processing. It handles the complex task of audio normalization and encoding, allowing you to focus on the content of your transcripts rather than technical bottlenecks.
OpenRouter Audio Transcription Use Cases
- Transcribing meeting recordings or voice notes directly from the command line.
- Converting audio files to text with specific formatting or speaker labels using custom prompts.
- Automating batch transcription workflows in DevOps or data pipelines.
- Testing different audio-capable models to compare transcription quality and cost.
How OpenRouter Audio Transcription Works
- The script captures the input audio file and uses ffmpeg to normalize the format to a 16kHz mono WAV file for optimal model compatibility.
- The processed audio is converted into a Base64 encoded string to prepare it for API transmission.
- The skill sends a request to the OpenRouter chat completions endpoint using the input_audio content type.
- To prevent shell argument limit issues, large data is piped through temporary files.
- The transcript is extracted from the JSON response and outputted to the console or a specified file.
OpenRouter Audio Transcription Setup
Ensure you have the required dependencies installed: curl, ffmpeg, base64, and jq. Then, set your API key as an environment variable:
export OPENROUTER_API_KEY="your_api_key_here"
Alternatively, you can configure the key in your Openclaw Skills configuration file:
{
"skills": {
"openrouter-transcribe": {
"apiKey": "YOUR_OPENROUTER_KEY"
}
}
}
Run your first transcription with:
./scripts/transcribe.sh path/to/audio.m4a
OpenRouter Audio Transcription Data Schema & Taxonomy
The skill manages data through a lifecycle of conversion and transmission:
| Data Component | Description |
|---|---|
| Input Source | Supports any audio format compatible with ffmpeg (m4a, mp3, wav, ogg). |
| Intermediate Format | Temporary 16kHz mono WAV file for standardized model input. |
| Payload Type | Base64 encoded audio string wrapped in an OpenRouter-compatible JSON object. |
| Output | Plain text transcription string extracted from the model response. |
| Metadata | Headers including X-Title and HTTP-Referer for dashboard tracking. |
OpenRouter Audio Transcription Advanced Features
- Model Switching: Use the --model flag to specify any supported model, such as openai/gpt-4o-audio-preview.
- Custom Instructions: Use the --prompt flag to provide context, such as language hints or formatting requirements.
- File Output Management: Direct transcripts to a specific file path using the --out argument.
- Large File Support: Implements --rawfile for jq and @file for curl to handle audio data that exceeds standard shell limits.
- Dashboard Tracking: Customize how usage appears in OpenRouter with the --title identifier.
SKILL.md
Loading
Related Openclaw Skills
WOL and Sleep PC Control
A specialized skill for sending Wake-on-LAN and Sleep-on-LAN magic packets to manage PC power states across a local network.
ObekT Security
A comprehensive threat detection and security analysis toolkit designed to audit code, files, and AI agent skills for vulnerabilities and malicious patterns.
Numerai Tournament
Automate participation in the Numerai hedge fund tournament to train models and earn NMR cryptocurrency.
Big Memory
An advanced context management system that uses structured snapshots to ensure AI agents never lose track of complex coding tasks during context compaction.
YNAB CLI Manager
A comprehensive command-line interface for managing You Need A Budget (YNAB) data, including budgets, categories, and transactions.
AgentFinObs
AgentFinObs is a comprehensive financial observability framework for monitoring, budgeting, and analyzing AI agent spending across multiple payment rails.
Featured*
