InstaGist Quick Start - Local/Self-Hosted

Get your Instagram Gist bot running in 5 minutes on a self-hosted n8n instance.

For Render.com deployment: See DEPLOY_TO_RENDER.md instead.

TL;DR

brew install yt-dlp ffmpeg

sudo apt update
sudo apt install ffmpeg
pip3 install yt-dlp

./scripts/check-dependencies.sh

Import Workflow
- Open n8n
- Workflows → Add Workflow → Import from File
- Select: n8n-workflows/instagram-gist-workflow.json
Add OpenAI Credentials
- Credentials → Add Credential → OpenAI API
- Paste your API key
- Save
Link Credentials & Activate
- Open imported workflow
- Link OpenAI credential to both "Transcribe" and "Summary" nodes
- Toggle workflow to "Active"
- Copy the webhook URL

curl -X POST YOUR_WEBHOOK_URL \
  -H "Content-Type: application/json" \
  -d '{"url": "https://www.instagram.com/reel/EXAMPLE/"}'

Or use the test script:

export WEBHOOK_URL="YOUR_WEBHOOK_URL"
./scripts/test-webhook.sh "https://www.instagram.com/reel/EXAMPLE/"

{
  "summary": "• Point 1\n• Point 2\n• Point 3",
  "transcript": "Full transcription...",
  "videoId": "EXAMPLE",
  "processingTime": "45 seconds"
}

Problem	Solution
"yt-dlp not found"	Install on n8n server, not local machine
"ffmpeg not found"	Install FFmpeg on n8n server
"Invalid API key"	Check OpenAI credentials in n8n
"Video not accessible"	Try a different public Instagram reel

Per video (30-60 seconds):

Use GPT-3.5-turbo instead of GPT-4 to reduce to ~$0.01 per video.

Need help? Check: