add-voice-transcription

Transcribe WhatsApp voice messages with OpenAI Whisper and store transcripts.

30|2|Updated Mar 13, 2026
One-click install
npx skills add https://github.com/IDEA-XL/MolClaw --skill add-voice-transcription-idea-xl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-voice-transcription
Source: https://github.com/IDEA-XL/MolClaw/tree/main/.claude/skills/add-voice-transcription
Command: npx skills add https://github.com/IDEA-XL/MolClaw --skill add-voice-transcription-idea-xl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribes voice messages in registered WhatsApp groups to convert audio into readable text, enabling the agent to understand and respond without listening to audio and preserving context for prompts and memory.

Core Features & Use Cases

  • OpenAI Whisper-based transcription of voice notes for automatic text conversion.
  • Integrates transcripts into the agent context by storing them with messages and exposing them as part of the conversation history (e.g., [Voice: <transcript>]).
  • Configurable via .transcription.config.json to manage provider, model, enabling/disabling, and fallback messages.
  • Use Case: When team members send voice notes, the agent can understand and respond based on the transcription.

Quick Start

Enable transcription by configuring .transcription.config.json with your OpenAI API key and restart MolClaw.

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 messages to text for an AI agent?

To transcribe WhatsApp voice notes, configure the system with an OpenAI API key to run Whisper transcription, automatically attaching the resulting text to message history for agent context.

Do I need an OpenAI API key to enable voice transcription?

Yes, you need an OpenAI API key to enable voice transcription, as the Skill relies on OpenAI Whisper to process audio files and requires adding the OpenAI dependency to your environment.

How are transcribed voice notes stored in the conversation context?

Transcribed voice notes are stored in conversation context by attaching the transcript to the message history and exposing it as readable text, such as [Voice: <transcript>], within the agent's memory pipeline.

Can I configure fallback behavior for WhatsApp audio transcription?

Yes, you can configure fallback behavior for WhatsApp audio transcription by modifying the .transcription.config.json file to manage provider settings, enable or disable transcription, and define fallback messages.

What happens when an agent receives a voice note without audio processing capabilities?

When an agent receives a voice note, the system automatically transcribes the audio into text using Whisper, allowing the agent to process the message content and preserve context without directly listening to audio.