voice-transcriber
Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3. Transcribes audio messages, saves both audio files and text transcripts. Perfect for voice-first AI workflows, founder journaling, and meeting notes.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/aiwithabidi/voice-transcriberWhat This Skill Does
The voice-transcriber skill for OpenClaw is a robust audio-to-text integration that leverages the state-of-the-art Deepgram Nova-3 engine. It is designed to capture, process, and archive voice-based interactions seamlessly. Beyond simple transcription, the tool handles file management by saving both the original audio files and the generated text transcripts in a structured format. This makes it an essential utility for agents that need to process verbal input, maintain documentation, or perform analysis on spoken audio across various formats including OGG, MP3, WAV, M4A, FLAC, and WEBM.
Installation
To integrate this skill into your local OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/aiwithabidi/voice-transcriber
Ensure that your environment has the necessary dependencies installed as defined in the source repository. Once installed, the skill exposes shell scripts and Python utilities that can be triggered directly by your OpenClaw agent instance.
Use Cases
This skill is highly versatile and supports various professional and personal workflows:
- Founder Journaling: Quickly capture thoughts and strategic pivots while on the move, ensuring a persistent record for future agent analysis.
- Meeting Intelligence: Transcribe recorded meetings automatically to extract action items, summaries, and key decisions.
- Voice-First Productivity: Build agent workflows where commands or data entries are spoken rather than typed, improving accessibility and efficiency.
- Content Creation: Record raw spoken drafts for blogs, social media posts, or video scripts that the agent can later refine and format.
Example Prompts
- "Transcribe the meeting recording located at /data/audio/sync_meeting_01.ogg and save the transcript to my notes folder."
- "Process my latest voice note from today; archive the file and send the transcript to my daily log."
- "Take this audio file at /incoming/memo.wav and give me a 3-bullet point summary of the main topics."
Tips & Limitations
To get the most out of your transcriptions, ensure high-quality audio input and minimize background noise, as this improves Deepgram's accuracy significantly. Keep in mind that file processing relies on local system access; verify that the agent has appropriate read/write permissions for the target directories. For long audio files, ensure your system has sufficient memory to handle the conversion process without interruption. Always remember to check for updates via the clawhub to access the latest version of the Nova-3 integration.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-aiwithabidi-voice-transcriber": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write, external-api
Related Skills
freshsales
Freshsales CRM integration — manage contacts, leads, deals, accounts, tasks, and sales sequences via the Freshsales API. Track deal pipelines, automate lead assignments, log activities, and generate sales reports. Built for AI agents — Python stdlib only, no dependencies. Use for sales CRM, contact management, deal tracking, pipeline reporting, and sales automation.
gemini-video-analyzer
Native video analysis using Google Gemini API. Upload and analyze video files — describe scenes, extract text/UI, answer questions about content, transcribe speech, identify objects and actions. Use when: (1) User sends a video file and wants it analyzed, (2) Video summarization or description needed, (3) Extracting text, UI elements, or information from screen recordings, (4) Answering questions about video content, (5) Comparing multiple videos, (6) Analyzing tutorials, demos, or walkthroughs.
agent-memory
Full AI agent memory stack — Mem0 unified memory engine with vector search (Qdrant) and knowledge graph (Neo4j), plus SQLite for structured data. Complete setup script and tools. Give your OpenClaw agent a real brain with semantic recall, entity relationships, and structured storage.
neon
Neon serverless Postgres — manage projects, branches, databases, roles, endpoints, and compute via the Neon API. Create database branches for development, manage connection endpoints, scale compute, and monitor usage. Built for AI agents — Python stdlib only, zero dependencies. Use for serverless Postgres, database branching, database management, development workflows, and cloud database automation.
onepassword
1Password Connect — vaults, items, secrets management for server-side applications.