A high-performance audio transcription and voice note archival tool powered by Deepgram Nova-3 for Openclaw Skills users.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install voice-transcriber-pro
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 voice-transcriber-pro 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 Voice Transcriber?
Voice Transcriber is a specialized utility within the Openclaw Skills ecosystem designed to bridge the gap between spoken ideas and digital text. By integrating the Deepgram Nova-3 engine, this tool enables users to transcribe audio messages, save voice notes, and archive recordings with high precision. It is optimized for those building voice-first AI workflows, founder journaling systems, or personal knowledge management setups where speed and accuracy are paramount.
This skill provides a bridge between raw audio data and actionable text content, allowing developers and power users to incorporate voice-to-text capabilities into their autonomous agent workflows. Whether you are capturing a quick thought on the go or processing recorded meetings, Voice Transcriber ensures your data is indexed and accessible.
Voice Transcriber Use Cases
- Transcribing voice messages or recorded audio files for searchable text access.
- Automating voice-first founder journaling with organized text and audio archives.
- Capturing meeting notes and speech-to-text data from varied audio sources.
- Processing audio files like OGG, MP3, and WAV for downstream AI agent tasks in Openclaw Skills environments.
How Voice Transcriber Works
- The user invokes the transcription script by passing a path to an audio file such as an MP3 or OGG.
- The skill sends the audio data to the Deepgram API using the configured DEEPGRAM_API_KEY.
- Deepgram processes the audio using the Nova-3 model to generate an accurate, low-latency transcript.
- The script utilizes jq to parse the API response and extract the clean text transcript from the JSON payload.
- The user can optionally save the transcript alongside the original audio file with added context for structured long-term archival.
Voice Transcriber Setup
- Obtain a Deepgram API key from the Deepgram developer console.
- Ensure the required system dependencies are installed on your machine:
sudo apt-get install curl jq
- Export your API key as an environment variable to make it accessible to the Openclaw Skills scripts:
export DEEPGRAM_API_KEY='your_api_key_here'
- You can now execute the transcription script via bash or use the Python script for advanced voice note archival with context.
Voice Transcriber Data Schema & Taxonomy
| Component | Description |
|---|---|
| Supported Formats | OGG, MP3, WAV, M4A, FLAC, WEBM |
| Environment Variables | DEEPGRAM_API_KEY (Required) |
| Output Files | Plain text (.txt) transcripts or structured voice note archives |
| Logic Dependencies | curl for API requests, jq for JSON parsing |
| Metadata | Optional context strings added during voice note saving for better organization |
Voice Transcriber Advanced Features
- Powered by Deepgram Nova-3 for state-of-the-art speed and accuracy compared to standard models.
- CLI-based workflow designed for easy integration into automated Openclaw Skills pipelines and larger agentic frameworks.
- Extensive support for multiple audio containers and high-fidelity codecs including FLAC and WEBM.
- Dual-mode operation allowing for either direct terminal output or full audio-text archival with user-defined context.
SKILL.md
Loading
Related Openclaw Skills
Voice Agent Builder
A developer-centric toolkit for building and managing sophisticated Voice AI agents across Vapi, Bland.ai, and Retell platforms.
Voice Agent Builder
A comprehensive toolkit for building, configuring, and managing AI-powered voice agents across multiple telephony providers.
USAspending
A comprehensive CLI tool for retrieving federal spending data, contracts, grants, and agency information directly from USAspending.gov.
Uploadthing
A zero-dependency Python utility for AI agents to upload, manage, and deliver files via the Uploadthing API and CDN.
Voice Transcriber
An AI-powered voice transcription and archival tool that converts audio files into searchable text for agent workflows.
Vonage
A comprehensive telecommunications bridge for AI agents to handle SMS, voice, verification, and number management via the Vonage API.
METADATA
Featured*
