add-voice-transcription

Transcribe WhatsApp voice messages into text using OpenAI Whisper.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/LIMITLESS-LONGEVITY/limitless --skill add-voice-transcription-limitless-longevity
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-voice-transcription
Source: https://github.com/LIMITLESS-LONGEVITY/limitless/tree/main/apps/nanoclaw/.claude/skills/add-voice-transcription
Command: npx skills add https://github.com/LIMITLESS-LONGEVITY/limitless --skill add-voice-transcription-limitless-longevity

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

NanoClaw agents cannot read audio-only WhatsApp voice notes, which prevents the agent from understanding and responding to spoken user messages. This skill converts incoming voice messages into text so the agent can process, display, and reply to their content.

Core Features & Use Cases

  • Automatic Download & Transcription: Detects WhatsApp voice messages, downloads the audio, and transcribes it using OpenAI's Whisper API.
  • Seamless Agent Integration: Delivers transcripts to the agent as readable messages (e.g., [Voice: <transcript>]) so the agent can respond to spoken input.
  • Operational Guidance: Includes steps to merge the whatsapp fork branch, add openai dependency, configure OPENAI_API_KEY in the environment, run tests, and verify logging for troubleshooting.
  • Use Case: A user sends a 30-second WhatsApp voice note and the agent receives the transcribed text and formulates an appropriate reply.

Quick Start

Transcribe the most recent WhatsApp voice note and return the transcript to the agent.

Frequently Asked Questions about add-voice-transcription

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automatically transcribe WhatsApp voice notes into text?

To transcribe WhatsApp voice notes automatically, this skill detects incoming audio messages, downloads the file, and calls OpenAI Whisper to convert the speech into readable text for agent processing.

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

Yes, configuring an OPENAI_API_KEY in your environment is required. You also need the openai npm dependency installed to enable Whisper API calls for converting voice messages into text.

How does a WhatsApp voice transcription integrate with my agent?

WhatsApp voice transcription integrates by delivering formatted transcripts (e.g., [Voice: <transcript>]) directly to the agent as readable messages, allowing the agent to understand and respond to spoken user input.

What is the best way to set up WhatsApp voice transcription for NanoClaw?

The best way to set up WhatsApp voice transcription is to merge the whatsapp/skill/voice-transcription branch, install the openai dependency, configure the API key, and run tests to verify logging functionality.

Why does my agent fail to process WhatsApp audio-only voice notes?

Agents fail to process WhatsApp audio-only voice notes because they cannot read audio formats natively. Transcription is needed to convert the spoken audio into text before the agent can interpret and reply to the content.