add-voice-transcription

Transcribe WhatsApp voice notes to text using OpenAI Whisper.

Updated Mar 10, 2026
One-click install
npx skills add https://github.com/erguotou520/myclaw --skill add-voice-transcription-erguotou520
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-voice-transcription
Source: https://github.com/erguotou520/myclaw/tree/main/.claude/skills/add-voice-transcription
Command: npx skills add https://github.com/erguotou520/myclaw --skill add-voice-transcription-erguotou520

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the need to manually listen to WhatsApp voice messages by turning them into readable text for the agent, so conversations can be handled faster and more reliably.

Core Features & Use Cases

  • Automatic transcription: Downloads incoming voice notes and converts them into transcript text with OpenAI Whisper.
  • WhatsApp channel integration: Hooks into NanoClaw’s WhatsApp flow so voice messages are processed as part of normal chat handling.
  • Practical use case: A user sends a voice note with instructions, and the agent receives the content as text and can respond without human audio review.

Quick Start

Ask the assistant to add voice message transcription to NanoClaw and configure it with your OpenAI API key.

Frequently Asked Questions about add-voice-transcription

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

FAQPage Schema
How do I automatically transcribe WhatsApp voice notes to text for my chat agent?

Automatic WhatsApp voice transcription downloads incoming voice notes and converts them to text using OpenAI Whisper, delivering the transcript directly to the agent for faster chat handling without manual audio review.

Do I need an OpenAI API key to transcribe WhatsApp voice messages?

Yes, transcribing WhatsApp voice messages requires an OpenAI API key because the process relies on OpenAI Whisper for the actual audio-to-text conversion and delivery to the agent.

Can I integrate voice transcription directly into my WhatsApp chat automation workflow?

Yes, voice transcription integrates directly into WhatsApp chat automation by hooking into the NanoClaw WhatsApp flow, processing voice messages as part of normal chat handling.

What is the best way to handle WhatsApp voice notes without listening to them manually?

The best way to skip manual listening is using OpenAI Whisper for voice transcription, which processes incoming WhatsApp voice notes and automatically delivers readable text to the agent.

Does voice transcription work with standard WhatsApp conversations?

Yes, voice transcription applies to registered WhatsApp conversations, automatically processing incoming voice notes so the agent receives the content as text and can respond immediately.

Are there limitations to processing WhatsApp voice notes with OpenAI Whisper?

Processing WhatsApp voice notes with OpenAI Whisper requires channel integration and successful validation through build and channel tests to ensure automatic transcripts are delivered correctly.