add-voice-transcription

Transcribe WhatsApp voice notes using OpenAI's Whisper API.

30.5k|12.9k|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/gavrielc/nanoclaw --skill add-voice-transcription-gavrielc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-voice-transcription
Source: https://github.com/gavrielc/nanoclaw/tree/main/.claude/skills/add-voice-transcription
Command: npx skills add https://github.com/gavrielc/nanoclaw --skill add-voice-transcription-gavrielc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables automatic transcription of voice notes in WhatsApp groups by leveraging OpenAI's Whisper API, so the agent can read and respond to spoken content in context.

Core Features & Use Cases

  • Automatic transcription of WhatsApp voice notes in registered groups.
  • Contextual integration: transcriptions are stored with messages to maintain conversation history.
  • Security & configuration: key safety and config steps are documented to securely provision API access.

Quick Start

Enable transcription by configuring your OpenAI API key and adding the transcription provider to the project. Then verify the agent processes voice notes in a registered group by sending a voice message and checking the transcript appears in the agent context.

Frequently Asked Questions about add-voice-transcription

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe WhatsApp voice notes automatically using OpenAI Whisper?

To transcribe WhatsApp voice notes automatically, configure your OpenAI API key and add the Whisper transcription provider to your project. The skill uses the openai npm package to process voice messages and stores transcripts with the conversation history for contextual agent responses.

What do I need to set up before enabling WhatsApp voice message transcription?

Before enabling WhatsApp voice message transcription, you need an active OpenAI API key configured in the transcription settings and the openai npm package installed in your project. Updating the NanoClaw workflow to download and process voice files is also required.

How does automatic voice transcription integrate with conversation context?

Automatic voice transcription integrates with conversation context by storing transcribed text with the original message history in the NanoClaw workflow. This ensures the agent can read and respond to spoken content using the full conversation context.

Can I use OpenAI Whisper for voice notes in registered WhatsApp groups?

Yes, you can use OpenAI Whisper for voice notes in registered WhatsApp groups. The skill processes audio messages in registered groups, transcribes them via Whisper, and verifies transcripts appear in the agent context for response generation.

Why are my WhatsApp voice note transcriptions not showing up in the agent context?

WhatsApp voice note transcriptions may not appear if the OpenAI API key is missing from the transcription config, the openai npm package is not installed, or the NanoClaw project is not updated to download voice messages. Verify these setup steps to resolve the issue.