AI / ML · 2026
BigUps
One topic string in, a fully narrated and captioned video out. A Python pipeline that orchestrates three different AI providers — an LLM for the script, Flux-Pro for the images, ElevenLabs for the voice — and assembles the result.
What it does
One command takes a topic and returns a finished video. Under the hood it chains four AI stages: an LLM (Claude / GPT) writes the script, Flux-Pro on Replicate generates a scene image per beat, ElevenLabs narrates it, and the pipeline generates captions and assembles the cut. A verified run produced 18 scene images, 18 voice clips, a caption track, and the final MP4.
The orchestration problem
Three vendors, one run
Each provider has different latency, rate limits, and failure modes. The pipeline sequences them into a single command and keeps partial work when one stage misbehaves.
Parallel where it pays
Image and voice generation are independent and both slow, so they run concurrently on a ThreadPoolExecutor instead of serially.
Timed off measured reality
The subtle one: captions and final assembly are timed from the *actual* duration of the generated audio, not a pre-estimate. TTS clip lengths are unpredictable — assume them and the whole video drifts out of sync.
Ten modules
script_gen · image_gen · voiceover · captions · video_assembly · pipeline · cli — packaged as an installable CLI.
Honest about BigUps
This is a working personal prototype, not a shipped product: it never left single-topic testing and it isn't under version control. I'm including it because the interesting engineering isn't the video — it's making a downstream stage (captioning) depend on the real output of an upstream one (audio duration) rather than an assumption, across three vendors that each fail differently.