add-voice-transcription

Transcribe WhatsApp voice messages using OpenAI's Whisper API.

Updated Mar 4, 2026

Search Tags:#automation #messaging #whatsapp #audio processing #voice transcription #openai whisper

Ready to run

npx skills add https://github.com/alanmun/vivian --skill add-voice-transcription-alanmun

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: add-voice-transcription
Source: https://github.com/alanmun/vivian/tree/main/.agents/skills/add-voice-transcription
Command: npx skills add https://github.com/alanmun/vivian --skill add-voice-transcription-alanmun

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables your agent to understand and respond to voice messages, overcoming the limitation of only processing text-based communication.

Core Features & Use Cases

Automatic Transcription: Voice notes sent via WhatsApp are automatically transcribed using OpenAI's Whisper API.
Seamless Integration: Transcribed text is delivered to the agent in a readable format, allowing for context-aware responses.
Use Case: Receive a voice memo from a colleague. The agent transcribes it, understands the request, and drafts a text-based reply, all without manual intervention.

Quick Start

Send a voice note in a WhatsApp chat to have the agent transcribe and respond to it.

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 audio data from the messaging channel and processes it using OpenAI's Whisper API, delivering readable text to your agent for context-aware responses.

Do I need an OpenAI API key to process audio notes?▼

Yes, you need an OpenAI API key to process audio notes, as the transcription mechanism relies entirely on OpenAI's Whisper API to parse the audio data and convert it into text.

Can I use OpenAI Whisper for voice transcription in an automation workflow?▼

You can use OpenAI Whisper for voice transcription in an automation workflow by integrating this Skill, which handles audio downloads, transcribes voice notes, and includes error fallback for seamless messaging channel processing.

What happens if audio processing fails during voice transcription?▼

If audio processing fails during voice transcription, the Skill executes an error fallback mechanism within the WhatsApp context, ensuring the messaging automation continues without breaking the conversation flow.

How does automated voice transcription work for messaging channels?▼

Automated voice transcription for messaging channels works by intercepting audio messages, downloading the voice data, and sending it to the Whisper API to generate text that the agent can understand and act upon.