Quick Overview
This workflow runs daily to turn the latest Artificial Intelligence News RSS headline into a YouTube Shorts video by generating a script with Groq, creating voiceover with VoiceRSS, selecting stock footage from Pexels, rendering with Shotstack, and uploading the finished MP4 to YouTube.
How it works
- Runs every 24 hours on a scheduled trigger.
- Reads the latest item from the Artificial Intelligence News RSS feed and extracts the headline and summary.
- Uses Groq (Llama 3.1) to generate a punchy ~45-second YouTube Shorts voiceover script based on the headline and summary.
- Converts the script into an MP3 voiceover with the VoiceRSS text-to-speech API and searches Pexels for a matching portrait video.
- Sends the stock video and script to Shotstack to render a 9:16 MP4 with text-to-speech audio and waits before polling Shotstack for the finished render URL.
- Downloads the rendered MP4 and uploads it to YouTube with the generated title and a prefilled description.
Setup
- Add a Groq API credential and ensure the Groq model node is connected to your account.
- Replace the VoiceRSS API key, Pexels API key, and Shotstack API key values in the corresponding HTTP Request nodes.
- Add YouTube OAuth2 credentials and select the correct YouTube account in the upload node.
- Review and customize the script prompt, default search keyword/hashtags, and YouTube upload settings (privacy, region, and category) to match your channel.