Instagram AI Automation
Multi-model GenAI content pipeline
Runs locally / on a schedule; source is private.
A multi-provider GenAI media pipeline (TypeScript/Node). It picks from a 100-topic database (10 categories) with a 30-day dedup history, writes the caption and trending hashtags with GPT-4o, generates vertical video via OpenAI Sora-2 (cascading to Runway Gen-3 then Luma Dream Machine by available API key), adds an optional ElevenLabs voice-over, and assembles + watermarks with FFmpeg and Sharp before publishing Reels through the Instagram Graph API (create-container → media_publish). A separate companion app, built on the OpenAI Agents SDK + ChatKit with a FastAPI backend and a Vite + React 19 panel, exposes the workflow as agent tools.
- TypeScript
- Node.js
- OpenAI GPT-4o
- Sora-2
- Runway Gen-3
- Luma Dream Machine
- ElevenLabs
- FFmpeg
- Instagram Graph API
- OpenAI Agents SDK + ChatKit
Architecture · topic → published Instagram Reel
Topic selection
Picks from a 100-topic database (10 categories) with a 30-day dedup history.
Caption + hashtags
GPT-4o writes the caption and trending hashtags.
Video generation
OpenAI Sora-2 generates vertical video, cascading to Runway Gen-3 then Luma by available API key.
Voice + assembly
An optional ElevenLabs voice-over; FFmpeg + Sharp assemble and watermark the Reel.
Publish
Published via the Instagram Graph API (create-container → media_publish).
- AI stack
- GPT-4o · Sora-2 · ElevenLabs
- Topic database
- 100 (10 categories)
- Est. cost / Reel
- ~$0.81
- Publishing
- Instagram Graph API