Automation of Video Content Creation for Auto Parts
Alexey Anshakov
š¤ Automating Creativity: 1 Photo + Code = Full Promo Video
This video was generated 100% programmatically using Remotion and Qwen3-TTS. No manual editing, no voice actors.
I built a pipeline that takes a static product photo, clones the brand's voice for a dynamic voiceover, and renders a perfectly synced 1280x720 video in under 60 seconds.
š ļø Stack: TypeScript, Remotion, Python, PyTorch (ROCm), Cloudflare R2.
#ProgrammaticVideo #AIEngineering #Automation #Remotion #TypeScript
Case Study: WRIO Programmatic Content Factory
Project Type: Automation & AI Engineering
Role: Lead Developer & Architect
Tools: Remotion, Qwen3-TTS, TypeScript, Python, Cloudflare R2
Status: Live / Production Ready
šÆ The Challenge
In the auto parts industry, inventory is massive (thousands of SKUs) but visually static. Sellers have photos, but social platforms (TikTok, Reels, YouTube Shorts) demand engaging video content.
Manual editing was impossible at scale:
Cost: ~$50 per video for a human editor.
Time: Hours of turnaround.
Voiceover: Expensive and slow to coordinate.
We needed a way to turn 1 photo + data into a professional promo video instantly.
š” The Solution
I engineered a Programmatic Content Factory that automates the entire creative process using code.
1. AI Voice Cloning (Qwen3-TTS)
Instead of generic robot voices, I integrated Qwen3-TTS to clone our brand's specific voice signature.
Input: Text script generated from product data.
Output: Human-like WAV file with proper intonation.
Tech: Python + PyTorch (with custom ROCm GPU acceleration logic).
2. React-Based Video Rendering (Remotion)
I used #Remotion to build video templates as React components. This allows for dynamic logic that standard editors can't do:
Dynamic Timing: The video automatically adjusts its length (playback rate) to match the generated audio duration exactly.
Smart Subtitles: Text animations are synced frame-by-frame with the speech.
Branding: Automatic logo placement and style application.
3. Infinite Scalability
The entire pipeline runs on a server. We can trigger 1 or 10,000 renders via API.
š The Result
Speed: Video generation time reduced from hours to < 60 seconds.
Efficiency: Zero manual editing required.
Quality: Full 1280x720 (HD), 24fps cinematic sync, consistent branding.
Outcome: We now have the capability to automatically generate a unique, voiced marketing video for every single part in our inventory.
Key Takeaway: By treating video as code, we unlocked a new marketing channel that was previously too expensive to access.
Like this project
Posted Jan 31, 2026
Developed an automated system for creating promo videos from photos and data.
