How to Make Viral AI Object Talking Videos That Get Millions of Views

January 21, 2026 Post a Comment

If you’ve been scrolling TikTok lately, chances are you’ve seen those AI videos where everyday objects suddenly talk like animated movie characters. A banana complains about being eaten, a screwdriver proudly explains its job, or a soap bottle sounds exhausted from being used all day. These videos are everywhere, and the crazy part is that many of them get millions of views.

The good news is, making videos like this is not as complicated as it looks. You don’t need advanced animation skills, expensive software, or a powerful PC. With the right prompt and a tool like InVideo AI, you can create your own AI object talking video in just a few minutes.

In this article, I’ll walk you through the entire process step by step. We’ll start from preparing the prompt, then generating the image, and finally turning it into a talking video. If you follow along, you’ll be able to create viral-style AI videos that look cinematic and feel alive.

Step 1: Preparing the Prompt

Just like any AI-generated content, everything starts with a prompt. The prompt is basically the “brain” of your video. It tells the AI what to create, how it should look, how it should feel, and what it should say.

To make things easier, I’ve already prepared a master prompt specifically designed for AI Object Talking videos. This prompt is structured, detailed, and optimized for short vertical videos like TikTok, Reels, and Shorts.

Here’s the PROMPT MASTER – Object Talk (Self-Explaining Object, Dynamic Emotion, 9:16):

ROLE:
You are TalkStuff / Object Talk, an AI that brings everyday objects to life as Pixar-style 3D animated characters that emotionally and clearly explain their own purpose, benefit, or usefulness.
---
USER INPUT (ONLY ONE):
Main object: {fill here}
---
AUTOMATIC RULES (MANDATORY):
Automatically choose the MOST RELEVANT EMOTION for the object
(anger, happiness, sadness, pride, exhaustion, calm, confidence, etc.)
Emotion must align with:
the object’s real function
how humans rely on or misuse it
The object MUST explain its own benefit, function, or value
Automatically determine the most relevant location/scene
Visual style must always be Pixar-style 3D cinematic
Aspect ratio must be vertical 9:16
Tone adapts to the chosen emotion (can be warm, proud, frustrated, or serious)
Optimized for short AI videos (Reels / TikTok / Shorts)
---
1️⃣ TEXT-TO-IMAGE PROMPT (Pixar-style 3D Render)
Write a highly detailed visual description for an image generator in NARRATIVE FORM.
You MUST explicitly describe:
Eyes: shape, size, and emotional expression matching the emotion
Eyebrows: position and emotional intensity
Mouth: shape, expression, speaking state
Arms & Gesture: body language that reinforces explanation or emphasis
Scene & Lighting:
Scene chosen automatically based on object context
Cinematic Pixar-style lighting
Lighting and color temperature must reinforce the emotion
Composition:
Vertical framing
Character centered and readable for 9:16 format
---
2️⃣ SCRIPT – 6 SECONDS (First-Person Monologue)
STRICT RULES (NO EXCEPTIONS):
First-person POV (“I”)
EXACTLY ONE sentence
The FIRST PART must act as a 3-second HOOK
The SECOND PART MUST clearly communicate the object’s benefit, function, or value
Emotional tone must match the chosen emotion
MUST NOT include:
addressing the audience
call to action
filler words
emojis
---
STYLE NOTES (INTERNAL):
The object speaks with authority about its own purpose
Explanation must feel natural, not like advertising
Emotional truth > technical detail
One sentence, two beats: hook → usefulness
One object = one clear takeaway

The best part about this master prompt is how simple it is to use. You only need to fill in one thing, which is the main object. For example, if you want to make a video about a screwdriver, just write:

Main object: screwdriver

After that, follow these steps:

Select all of the prompt text and copy it.
Open ChatGPT.
Paste the prompt and hit Send.
ChatGPT will generate two things for you: A text-to-image prompt and a ready-to-use video script

Once you have those, you’re ready for the next step.

Step 2: Generating the Image

Now it’s time to turn the text-to-image prompt into an actual character image. For this, we’ll use InVideo AI.

Here’s how to do it:

Copy the text-to-image prompt that ChatGPT generated.
Open InVideo AI and log in.
Go to the Agents & Models menu.
Tap See all under Generative Models.
Choose Image to see all available image generator models like Nano Banana Pro, GPT Image 1.5, Seedream 4.5, and more.
Select Nano Banana Pro.
Create a new project.
Paste your text-to-image prompt.
Set the aspect ratio to 9:16 and choose the resolution you want (1K, 2K, or even 4K).
If you subscribe, you can get unlimited access to Nano Banana Pro inside InVideo.
Click Generate and wait a few seconds.
Done. Your AI object image is ready. Download it, because we’ll use it in the next step.

Step 3: Generating the Video

This is where your object finally comes to life and starts talking.

Follow these steps carefully:

Copy the video script generated by ChatGPT.
Go back to InVideo AI and tap on Video.
You’ll see multiple video generator models like Kling 2.6, Veo 3.1, Sora 2, Seedance 1.5, and more.
Choose Veo 3.1 Fast.
Select the project you created earlier or make a new one.
Upload the image you downloaded.
Paste the script into the text field.
Set the aspect ratio to 9:16, duration to 8 seconds, resolution to 1080p (you can go up to 4K), and enable Generate with sound so the character speaks.
Click Generate and wait for about 1–2 minutes.
Finished. Your AI object talking video is ready.

And that’s it. You now have a cinematic, talking AI character that’s perfect for TikTok or Shorts.

Video Tutorial Reference

If you prefer watching instead of reading, you can follow the full video tutorial here:

Conclusion

AI object talking videos are popular for a reason. They’re funny, emotional, easy to understand, and surprisingly relatable. People love seeing everyday objects come to life and explain themselves in a dramatic or humorous way.

With a solid master prompt and tools like ChatGPT and InVideo AI, creating these videos becomes incredibly simple. You don’t need animation skills or a creative team. All you need is one good idea, one object, and a few minutes of your time.

If you’re looking for a content format that has high viral potential and doesn’t require heavy editing, this is one of the best options out there right now. Try different objects, experiment with emotions, and see which ones resonate with your audience.

Once you get the hang of it, you’ll realize just how powerful a well-written prompt can be.

Mangidik