add-voice-transcription

Transcribe WhatsApp voice notes into [Voice: <transcript>] text using OpenAI Whisper.

Updated Mar 24, 2026
One-click install
npx skills add https://github.com/E01N/ClawOutreach --skill add-voice-transcription-e01n
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-voice-transcription
Source: https://github.com/E01N/ClawOutreach/tree/main/nanoclaw/.claude/skills/add-voice-transcription
Command: npx skills add https://github.com/E01N/ClawOutreach --skill add-voice-transcription-e01n

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribes WhatsApp voice notes into readable transcripts for the NanoClaw agent so it can read and respond accurately.

Core Features & Use Cases

  • Transcribes voice messages into text formatted as [Voice: <transcript>].
  • Integrates OpenAI Whisper to convert audio to text with key-based authentication.
  • Enables end-to-end automation for voice-note handling within the NanoClaw WhatsApp channel.

Quick Start

Provide your OpenAI Whisper API key and send a WhatsApp voice note to verify transcription.

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 into text for an agent to read?

WhatsApp voice transcription is achieved by downloading the audio and passing it to OpenAI Whisper, which returns a text transcript formatted as [Voice: <transcript>] for the agent to read and respond to accurately.

Do I need an OpenAI API key to convert voice notes into readable transcripts?

Yes, you need a valid OPENAI_API_KEY to authenticate and route the audio files to the OpenAI Whisper API for accurate voice-to-text conversion during the transcription process.

Can I use OpenAI Whisper with a WhatsApp channel for automated voice message handling?

Yes, you can integrate OpenAI Whisper with a WhatsApp channel to download incoming voice messages, transcribe the audio, and deliver text outputs directly to the NanoClaw agent for automated end-to-end handling.

How does voice transcription work for WhatsApp audio in an automated workflow?

The voice transcription workflow downloads the incoming WhatsApp audio, calls OpenAI Whisper to convert the speech to text, and formats the result as [Voice: <transcript>] for the agent to read and process.

What is the best way to test if WhatsApp voice transcription is working correctly?

To test WhatsApp voice transcription, provide your OpenAI Whisper API key, ensure a validated build/test workflow is active, and send a WhatsApp voice note to verify the agent receives the readable text transcript.