Voice Transcriber for Openclaw

An AI-powered voice transcription and archival tool that converts audio files into searchable text for agent workflows.

aiwithabidi
v1.0.0
Mar 7, 2026
1
377
10

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install voice-transcriber

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install voice-transcriber 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 tool designed to bridge the gap between spoken word and digital intelligence within the Openclaw Skills ecosystem. By leveraging the Deepgram Nova-3 model, it provides high-accuracy transcription for various audio formats, enabling users to maintain a searchable archive of voice notes, meeting recordings, and spoken thoughts.

This skill is particularly valuable for developers and founders who prefer a voice-first approach to productivity. It not only handles raw transcription but also supports archival workflows, making it an essential component for any AI agent that needs to process and understand auditory data within the broader framework of Openclaw Skills.

Voice Transcriber Use Cases

  • Transcribing voice messages from messaging platforms into text for AI analysis.
  • Maintaining a founder journal by saving voice notes with accompanying transcripts.
  • Converting meeting recordings into documentation within Openclaw Skills environments.
  • Automating speech-to-text processing for multi-modal AI agent pipelines.

How Voice Transcriber Works

  1. The user provides an audio file path (supporting OGG, MP3, WAV, etc.) to the transcription script.
  2. The skill sends the audio data to the Deepgram API using the provided credentials.
  3. The system receives the JSON transcript and processes it using jq for clean text output.
  4. Transcripts are either displayed in the terminal, saved to a specific text file, or archived alongside the original audio for future reference.

Voice Transcriber Setup

First, ensure you have the necessary system dependencies installed for your Openclaw Skills environment:

sudo apt-get install curl jq

Next, export your Deepgram API key to your environment variables to enable the transcription service:

export DEEPGRAM_API_KEY='your_api_key_here'

You can then run the transcription script directly from your terminal:

bash scripts/transcribe.sh /path/to/audio.ogg

Voice Transcriber Data Schema & Taxonomy

The skill manages data by pairing audio source files with generated text outputs. The organization follows this structure:

Data Type Description Format
Source Audio Original recorded voice data OGG, MP3, WAV, M4A, FLAC
Transcript Pure text extraction of the audio content TXT
Context Optional metadata or tags for voice notes String
Metadata API response data including confidence scores JSON

Voice Transcriber Advanced Features

  • Multi-format support including WEBM and FLAC for high-fidelity archival within Openclaw Skills.
  • Integrated archival script (save_voice_note.py) that pairs manual context with audio files.
  • Modular shell script design allowing for easy integration into larger automation scripts.
  • Low-latency processing powered by Deepgram Nova-3 architecture for real-time transcription needs.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Requires
Bins curljq
Github Stars: 0
forks: 0

Featured*