add-voice-transcription

Transcribe WhatsApp voice notes to text using OpenAI Whisper.

Updated Mar 15, 2026
One-click install
npx skills add https://github.com/spyqs/nanoclaw-email-imap --skill add-voice-transcription-spyqs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-voice-transcription
Source: https://github.com/spyqs/nanoclaw-email-imap/tree/main/.claude/skills/add-voice-transcription
Command: npx skills add https://github.com/spyqs/nanoclaw-email-imap --skill add-voice-transcription-spyqs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of manually listening to WhatsApp voice notes by automatically transcribing them into text so the agent can understand and respond accurately.

Core Features & Use Cases

  • Whisper-based transcription for voice notes: Converts incoming WhatsApp audio messages into readable transcripts for the agent.
  • Seamless agent delivery: Presents transcriptions to the agent in a consistent format as [Voice: <transcript>].
  • Operational support for real workflows: Handles the full flow from adding the feature to configuring the required OpenAI API key and verifying results in logs.

Use case: When a customer sends voice updates in a WhatsApp chat, the agent receives the transcribed text and can draft replies or extract key details without requiring a human to listen first.

Quick Start

Run the Claude Code instruction to add voice transcription, then provide your OpenAI Whisper API key so the agent can start transcribing voice notes as [Voice: <transcript>].

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 into text for an AI agent?

To transcribe WhatsApp voice notes into text, you can use this Skill to integrate OpenAI Whisper, which automatically downloads incoming audio and delivers it to the agent as a formatted text transcript.

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

Yes, you need an active OPENAI_API_KEY configured in your deployment to download and process WhatsApp audio files using OpenAI Whisper for transcription.

Can I use this voice transcription feature without a WhatsApp channel already installed?

No, this feature applies to NanoClaw deployments that already have the WhatsApp channel installed and registered chats actively receiving voice notes.

How does the agent receive the transcribed WhatsApp audio?

The agent receives the transcribed WhatsApp audio in a consistent format as [Voice: <transcript>], allowing it to understand and respond to voice messages without manual listening.

How do I verify if WhatsApp voice transcription is working correctly?

You verify successful WhatsApp voice transcription by checking your deployment logs, which will display either the successful transcript output or clear failure reasons.

What happens when a customer sends a voice update in a WhatsApp chat?

When a customer sends a voice update, the system transcribes the audio using OpenAI Whisper, allowing the agent to draft replies or extract key details directly from the text without human intervention.