Spoooler: our open-source engine for automated social videos
Turns a brief into a voiced, subtitled short video, end to end.
- System and automation
- In-house R&D, prototype
- In-house prototype, open source
At a glance
Client Spoooler, an OutGrow open-source project
Client
Spoooler, an OutGrow open-source project
Industry Video automation
Industry
Video automation
Year 2025
Year
2025
Status In-house prototype, open source
Status
In-house prototype, open source
Every case on this site answers the same four questions, so you can compare them.
Before
Making short videos means writing a script, recording a voiceover, finding footage, syncing captions and rendering, every time.
What it does now
An LLM writes the script from a short brief.
A text-to-speech model voices it, with a timestamp for every word.
B-roll is pulled from stock and image APIs.
Captions are synced to the word timestamps.
Remotion renders the finished MP4.
Where a person decides
It only renders files. Whether a video gets posted is a person's call.
Result
In-house prototype. No outcome figures yet.
How we built it
Built React and Remotion templates for different layouts and aspect ratios.
Connected script writing, voice and footage APIs.
Wrote the caption engine that syncs to word timestamps.
Set up remote rendering so videos render in parallel.
Stack
- React
- Remotion
- TypeScript
- Groq
- Kokoro TTS
- FFmpeg
- AWS Lambda
From the project
More work like this
One inbox for every inquiry a Dubai studio gets
An email engine that pauses itself before it hurts the domain
A distributor's back office rebuilt to sell nationally
Your case study starts with an audit.
One to two weeks inside your operations. You get a map of where time and money leak, the return on each fix, and a fixed scope before we build anything.
Most businesses we meet have paid for an AI tool nobody uses. We start from your numbers, so the first build is chosen by payback.
Zain Khan and Anwar Sheikh
Founders, OutGrow
Outgrow
Intelligence
Studios.