add-voice-transcription

Transcribe WhatsApp voice messages into text using OpenAI's Whisper API.

13|2|Updated Feb 28, 2026
One-click install
npx skills add https://github.com/NebulaMao/nanoiflow --skill add-voice-transcription-nebulamao
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-voice-transcription
Source: https://github.com/NebulaMao/nanoiflow/tree/main/.claude/skills/add-voice-transcription
Command: npx skills add https://github.com/NebulaMao/nanoiflow --skill add-voice-transcription-nebulamao

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the transcription of voice messages received via WhatsApp, allowing AI agents to process and respond to audio content seamlessly.

Core Features & Use Cases

  • Automatic Transcription: Converts WhatsApp voice notes into text using OpenAI's Whisper API.
  • Agent Integration: Delivers transcribed messages to the agent in a readable format [Voice: <transcript>].
  • Use Case: Receive a voice note from a colleague. Instead of listening to it, the AI agent automatically transcribes it, understands the content, and formulates a text-based response.

Quick Start

Apply the voice transcription skill to your NanoClaw instance.

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 automatically?

To transcribe WhatsApp voice messages automatically, this Skill downloads received audio and sends it to the OpenAI Whisper API, returning the text directly to your agent for processing.

Do I need an OpenAI API key to convert WhatsApp voice notes to text?

Yes, you need an active OpenAI API key to convert WhatsApp voice notes to text, as this Skill relies specifically on the Whisper API model to perform the audio transcription.

How does the AI agent receive the transcribed WhatsApp audio?

The agent receives the transcribed WhatsApp audio in a readable text format structured as [Voice: <transcript>], allowing it to seamlessly understand the content and formulate a text-based response.

What happens if the Whisper API fails to transcribe a voice message?

If the Whisper API fails to transcribe a voice message, the Skill includes error fallback mechanisms to handle the failure gracefully, ensuring your agent workflow continues without crashing.

Can I use this Skill to process audio files from other platforms?

This Skill is specifically designed to handle audio message downloading and transcription for WhatsApp channels, so it does not natively support processing audio files from other communication platforms.