add-voice-transcription

Transcribes WhatsApp voice notes into text using OpenAI Whisper.

2|2|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/sskarz/nanoclawbster --skill add-voice-transcription-sskarz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-voice-transcription
Source: https://github.com/sskarz/nanoclawbster/tree/main/.claude/skills/add-voice-transcription
Command: npx skills add https://github.com/sskarz/nanoclawbster --skill add-voice-transcription-sskarz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @whiskeysockets/baileys, openai.

What problem does it solve?

WhatsApp voice notes can be time-consuming to process manually; this skill automatically transcribes them so your agent can understand and respond.

Core Features & Use Cases

  • Automatic transcription: Converts WhatsApp voice notes to text via OpenAI Whisper for downstream agents.
  • Fallback handling: If transcription is unavailable, returns a clear fallback message.
  • Seamless integration: Plugs into the WhatsApp channel and works with the existing message flow.

Quick Start

Start NanoClawbster and provide your OpenAI API key to enable voice 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 notes into text for my chatbot?

WhatsApp voice notes are transcribed into readable text using OpenAI Whisper, allowing your agent to process and respond to audio messages automatically. The skill plugs into the existing WhatsApp channel message flow.

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

Yes, an OpenAI API key is required to enable voice transcription. You must provide the OPENAI_API_KEY in your environment to allow the OpenAI Whisper model to convert audio into text.

What happens if OpenAI Whisper transcription fails on a voice message?

If transcription is unavailable, the skill returns a clear fallback message instead of failing silently. This ensures the agent and the user are notified when audio-to-text conversion cannot be completed.

Can I use OpenAI Whisper for WhatsApp voice notes without manual downloads?

Yes, the skill automatically intercepts voice messages received on the WhatsApp channel and converts the audio to text. This eliminates the need to manually download and process audio files for your chatbot.

How does audio-to-text conversion improve chatbot agent processing?

Audio-to-text conversion allows downstream agents to read and act on voice messages. By transforming WhatsApp audio into text transcripts, the agent can understand voice input and generate appropriate responses seamlessly.