Writing
Each monologue is meticulously crafted by a person. This stage of the process is unadulterated artistic expression. No AI impurities go into the scriptwriting process.
Nina Knows
A British Goldendoodle examines American culture one grievance at a time. Follow the series on Instagram Reels, TikTok, and YouTube Shorts.
Welcome to Doodle Drum!
This is the AI-first production studio behind Nina Knows. The heart of the series is its writing, which is completely human-created. All of the grievances, observations, and punchlines are real. In fact, about a year of off-and-on development went into Nina Knows. Other projects were completed in between, but this series is the result of extensive artistic exploration and technical experimentation along the jagged frontier of AI.
AI filmmaking is in a transitional period. While we respect everyone's opinion about the use of AI in art, we fundamentally disagree that it will have a negative impact in the long run. Read more in the FAQ.
Production Overview
Created by a person
Storyboarding
Arranging shot sequences presents challenges when composing sequential action. Running text analysis on the script and choosing which camera angles and cuts to serve the storytelling.
Editing
Finding the rhythm, pacing, and comedic timing is yet another process done by a person. It inevitably leads to rewrites and video regenerations.
Music
As opposed to cutting to music, each monologue is set to the same mischievous loop that was edited by a person from a royalty free beat produced by another person.
Made with AI
Images
As of July 2026, all images are generated using GPT Image 2 and Nano Banana 2. Obviously, this will evolve.
Video
As of July 2026, all Images are generated using the Gemini Omni model. Of course, this will change too.
Voice
As of July 2026, Nina’s voice is generated using Eleven Multilingual v2. This is less likely to change anytime soon.
Series Development
Here are just a handful of videos to illustrate the evolution of the project over the course of the year.
Summer 2025
Nina is a real Doodle that was born in Kent, England. She lived most of her life in Chelsea, London and is spending her senior years in Chelsea, New York. The series was born out of the culture shock she must have experienced when she realized Manhattan was a much filthier place to live.
Fall 2025
Nina was the perfect test subject for experiments in AI video generation. While upscaled effectively, you can see this early video is cropped to remove the watermark and struggles to retain consistency across the different shots. The lip syncing is pretty rough too. This video was generated using Veo 3 from Google, upscaled with Topaz, and voice generation from ElevenLabs.
Fall 2025
Still to this day, even as AI video has improved, the models struggle to create a female dog as you’ll notice in the last shot. You’ll also notice that the monologue is rushed because the clips are too short. Still, this one felt like the high watermark of the early experiments.
Summer 2026
After Seedance 2.0 came out, we ran a bunch of tests. The problem was the cost. It was too expensive to allow for creative exploration within an episode. Then Gemini Omni dropped and the cost per generation became reasonable enough that we weren’t constantly monitoring credits. That’s when we knew it was time to produce a slate of episodes.
FAQ
- I’m interested in sponsoring an episode of Nina Knows. Who do I contact?
- We'd love to hear from you. Email us at partnerships[at]doodledrum.ai.
- What’s your stance on the use of AI in the arts?
- We believe that AI will lead to a renaissance in auteur filmmaking. Furthermore, this series would not exist without AI. It would be impossible to achieve this level of production value for niche content like this. Funding does not exist for 3D projects about neurotic British doodles. While we understand there are concerns about data sourcing, we are not responsible for the actions of the companies that make this series possible.
- What models do you use?
- As of July 2026, images are generated with GPT Image 2 and Nano Banana 2, video with Gemini Omni, and Nina’s voice with Eleven Multilingual v2 through ElevenLabs. Early experiments in the series used Google’s Veo 3, upscaled with Topaz, also with voice from ElevenLabs. The stack will keep evolving, and music will remain entirely human.