add-voice-transcription

please type here

Updated Feb 14, 2026

Search Tags:#transcription #whatsapp #nanoclaw #speech to text #voice message #openai whisper

Ready to run

npx skills add https://github.com/b9b4ymiN/JellyCore --skill add-voice-transcription-b9b4ymin

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: add-voice-transcription
Source: https://github.com/b9b4ymiN/JellyCore/tree/main/nanoclaw/.claude/skills/add-voice-transcription
Command: npx skills add https://github.com/b9b4ymiN/JellyCore --skill add-voice-transcription-b9b4ymin

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill enables an AI agent to understand and respond to voice messages by transcribing them into text, bridging the gap between spoken and written communication.

Core Features & Use Cases

Automatic Transcription: Converts voice notes from platforms like WhatsApp into readable text using OpenAI's Whisper API.
Seamless Integration: Allows agents to process voice message content as if it were typed text, maintaining conversational context.
Use Case: A user sends a voice note asking for a summary of a meeting. The agent transcribes the voice note, understands the request, and provides the summary.

Quick Start

Add voice message transcription to NanoClaw using OpenAI's Whisper API.

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 into text for an AI agent?▼

You can transcribe WhatsApp voice messages into text by using OpenAI's Whisper API within the NanoClaw platform. The skill automatically downloads the media, sends it to the API, and integrates the transcribed text into the agent's message processing pipeline.

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

Yes, you need an OpenAI API key to convert voice notes to text because the transcription relies on OpenAI's Whisper API. You must also install specific npm packages to enable the integration within NanoClaw.

How does speech to text processing work with NanoClaw and OpenAI Whisper?▼

Speech to text processing with OpenAI Whisper works in NanoClaw by downloading incoming voice media, transcribing it via the API, and feeding the resulting text back into the agent's conversational context as if it were typed.

Can I use voice transcription to help an agent understand spoken meeting summaries?▼

Yes, you can use voice transcription to help an agent understand spoken meeting summaries. The skill converts the voice note into readable text, allowing the agent to process the request and provide a response based on the transcribed content.

What is the best way to bridge spoken communication into an AI text pipeline?▼

The best way to bridge spoken communication into an AI text pipeline is using OpenAI's Whisper API. This approach automatically transcribes voice notes into written text, allowing conversational agents to maintain context and respond to spoken requests seamlessly.

Are there limitations when using OpenAI Whisper for voice message transcription in NanoClaw?▼

Limitations of using OpenAI Whisper for voice message transcription in NanoClaw include the requirement of an active OpenAI API key, necessary npm package installations, and dependency on the API for processing voice media into text.