Multi-Modal Content Creator

面向自由创作者的自动化多模态内容创建工具，核心功能为通过WhatsApp接收客户的文本/语音需求，调用Whisper转写语音为文本，用DALL-E3生成对应图片并自动回复；也支持单独进行音频转写、单图/批量图片生成。适用于创作者高效响应客户需求，输入可来自WhatsApp消息、本地音频/文本文件，输出为图片或转写文本，可发送至WhatsApp或本地保存。

terrycarter1985

热度 29.81

最近更新 2026-05-12 08:01:46

分类：自动化依赖：代码执行 / 读写文件 / 第三方 API应用场景：图像生成 / 工作流 / 自动化脚本 / API 集成

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add multimodal-content-creator

Metadata

name: multimodal-content-creator
description: End-to-end multimodal content creation workflow — receive WhatsApp requests (text or voice), transcribe audio via Whisper, generate images with DALL-E 3, and reply automatically.
tags: ["whatsapp","whisper","dall-e","image-generation","transcription","workflow","content-creation"]

Multi-Modal Content Creator

Automated content creation workflow for freelance creators. Receives customer requests via WhatsApp (text or voice notes), transcribes audio to text, generates images from prompts, and sends results back.

Components

wacli.py — WhatsApp CLI client for receiving/sending messages
transcribe.py — Audio transcription via OpenAI Whisper API (handles large files by chunking)
generate_images.py — DALL-E 3 image generation with batch support
workflow.py — End-to-end orchestrator

Prerequisites

Python 3.10+
OpenAI API key (OPENAI_API_KEY env var)
WhatsApp CLI auth token

Setup

pip install -r requirements.txt
export OPENAI_API_KEY="your-api-key"
python wacli.py login <your-wacli-token>

Usage

Process all incoming WhatsApp requests

python workflow.py process-all

Generate a single image

python generate_images.py "a cat riding a skateboard"

Batch generate from file

python generate_images.py prompts.txt

Transcribe audio

python transcribe.py recording.mp3

WhatsApp CLI

python wacli.py list
python wacli.py send +1234567890 "Hello!"