Complete Workflow Tutorial

Build an end-to-end AI content pipeline using Get3W's API.

Overview

This tutorial walks through a complete workflow: generating an image, animating it into a video, adding speech, and creating a digital human — all through the Get3W API.

Prerequisites

• A Get3W account with credits
• API key from get3w.com/accesskey
• Python 3.8+ with the get3w package installed

pip install get3w
export GET3W_API_KEY="your-api-key"

Step 1: Generate an Image

import get3w

image = get3w.run("get3w/flux-dev", {
    "prompt": "Professional headshot of a friendly business woman, studio lighting, white background",
    "width": 1024,
    "height": 1024
})

image_url = image["outputs"][0]
print(f"Image: {image_url}")

Step 2: Generate Speech

speech = get3w.run("minimax/speech-02-hd", {
    "text": "Hello! Welcome to Get3W. I'm here to show you how easy it is to create AI-powered content. Let's get started!",
    "voice_id": "default"
})

audio_url = speech["outputs"][0]
print(f"Audio: {audio_url}")

Step 3: Create a Talking Avatar

video = get3w.run("get3w/infinitetalk", {
    "image_url": image_url,
    "audio_url": audio_url
})

video_url = video["outputs"][0]
print(f"Video: {video_url}")

Step 4: Upscale the Video (Optional)

upscaled = get3w.run("get3w/video-upscaler", {
    "video_url": video_url
})

final_url = upscaled["outputs"][0]
print(f"Final video: {final_url}")

Complete Script

import get3w

print("Step 1: Generating portrait...")
image = get3w.run("get3w/flux-dev", {
    "prompt": "Professional headshot of a friendly business woman, studio lighting, white background",
    "width": 1024,
    "height": 1024
})
image_url = image["outputs"][0]
print(f"  Image: {image_url}")

print("Step 2: Generating speech...")
speech = get3w.run("minimax/speech-02-hd", {
    "text": "Hello! Welcome to Get3W. I'm here to show you how easy it is to create AI-powered content.",
    "voice_id": "default"
})
audio_url = speech["outputs"][0]
print(f"  Audio: {audio_url}")

print("Step 3: Creating talking avatar...")
video = get3w.run("get3w/infinitetalk", {
    "image_url": image_url,
    "audio_url": audio_url
})
video_url = video["outputs"][0]
print(f"  Video: {video_url}")

print("Done! Your AI-generated video is ready.")

Cost Estimate

Step	Model	Approximate Cost
Image generation	FLUX Dev	~$0.03
Speech generation	Minimax Speech 02	~$0.01
Talking avatar	InfiniteTalk	~$0.10
Total		~$0.14

Next Steps

• How to Reduce Costs — Optimize your spending
• How to Use Webhooks — Async processing for production
• REST API — Full API documentation