add-voice-transcription

Community

Turn voice notes into transcripts for FFT_nano

Author0-CYBERDYNE-SYSTEMS-0
Version1.0.0
Installs0

System Documentation

What problem does it solve?

FFT_nano handles WhatsApp voice notes by converting them into readable text, enabling the agent to understand and respond to audio content in chats.

Core Features & Use Cases

  • Automatic transcription of voice messages using OpenAI's Whisper API to produce accurate text representations.
  • Contextual storage of transcripts so the agent can reference spoken content during conversations.
  • Support for registered WhatsApp groups, allowing the agent to act on voice notes consistently across chats.

Quick Start

Use this skill to enable voice transcription in FFT_nano. Steps:

  1. Ensure you have an OpenAI API key for Whisper transcription and that you have added it to your transcription config.
  2. Add the OpenAI npm package to your project dependencies by running npm install openai.
  3. Create a .transcription.config.json in the project root with provider: "openai", model: "whisper-1", enabled: true, and your apiKey.
  4. Build and start FFT_nano as usual; in registered groups, send a voice note to see the transcription appear as a transcribed text context for the agent.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: add-voice-transcription
Download link: https://github.com/0-CYBERDYNE-SYSTEMS-0/FFT_nano/archive/main.zip#add-voice-transcription

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.