# AI vehicle video pipeline

Haris Muhibić co-leads a serverless pipeline that turns dealership inventory into a narrated marketing video for every vehicle. He owns the voice, quality and cost layers.

- Role: Co-lead; owner of voice, QA and cost
- When: 2025 – present
- Stack: AWS Step Functions, Lambda, SQS, DynamoDB, Bedrock, Gemini, Whisper, SSML, Text-to-speech

## The problem

A dealership has hundreds or thousands of cars and nobody with time to film each one. A short narrated video per vehicle sells better than photos alone, but only if the narration sounds right, including model names like "2500HD" or "4MATIC".

## My part

A colleague built the first scaffold, and the renderer is owned by another engineer. I own pronunciation, speech quality checks, background removal, the concurrency and retry machinery, model migrations, and the production cost and model study.

## How it works

Image classification, then vehicle classification, script, pronunciation, audio, feature timing, render and post-processing. About 22 Lambda functions run under Step Functions, and a failed run can resume from the stage where it stopped, reusing cached images, script and audio.

## What's unusual

- **A pronunciation compiler, not a prompt.** Prioritised rules and an alias dictionary built from real inventory produce SSML, so "2500HD" becomes "twenty-five hundred H D". The model is called only for real ambiguity, such as "SEAT" the brand versus "driver seat".
- **Customers can record how their name is said.** The recording is converted to phonetic spelling (IPA), and candidates that sound wrong are rejected.
- **Closed-loop speech QA.** Whisper transcribes every generated clip, which is aligned to the expected text and regenerated if it fails. Whisper has a hard time budget so the check never times out the function.
- **Audio cache keyed by content.** When a pronunciation rule changes, only the affected audio is regenerated.
- **Model choices settled by measurement.** Cheap models are checked against a rule oracle on adversarial cases before any migration, then run in shadow before the switch.

---
Haris Muhibić · chern0.dev · haris@chern0.dev · Book a call: https://calendar.app.google/qiN9zJrS5gSqQPky8