One nice feature of n8n that I didn't quite understand at first is item splitting. I kept trying to add a Loop flow where I didn't actually need one because n8n would automatically repeat for each item after the Split. But if you need to stop repeating every node for every item, then you have to bring the items back together. In the attached image, I needed to grab image Ids from different sources and put them all in one list. The first Split separated all the image columns, but some of those columns had more than one image so the second split ran 5 times for each column and found 4 more items to split out. No need to loop through the columns, n8n handled the items for me. After getting all the images, I didn't want to call the API to download the images 9 different times, instead I aggregated all the image Ids back into one item, and sent that list to the API instead. So Items in n8n can be really powerful if planned for and handled correctly, making for a cleaner workflow without out the crazy looking mess of loops everywhere. Just have to know when to Aggregate (or Filter, or Merge, or Switch...) to get back to one item and one execution per node. Been spending a good amount of time splitting items out and aggregating them back so thought this might be helpful. Let me know if you have any questions. More n8n basics soon!

We were playing around with Google Opal earlier this week and it's a promising tool. With one prompt, I had a workflow that would combine multiple images using Google's new Nano Banana image model. Opal is limited to Google tools only at this point in terms of input and output, but Google has an impressive suite of abilities so if you're already invested in the Google ecosystem, this could be an easy and fast way to combine your workflows without having to connect with webhooks and triggers. Plus one of the output options is a custom Webpage so you're well on your way to a custom SaaS. You can try it out for free right now at https://opal.withgoogle.com/

What's the plan for this week? One big goal for Friday? I've got my eye on an ElevenLabs alternative, whether it's Microsoft's new VibeVoice model or Kokoro (thanks for the suggestion @Danilo Alves!), a self-hosted voice system will be in the works. I'll have a video posted by the end of the week. And maybe some bonus nano-banana since that seems to be a popular one. Let me know what else you'd like to see or need help with. Happy Monday and good luck this week!

Google's new Gemini-2.5-Flash-Image-Preview model, codenamed "nano banana" before launch dropped yesterday on aistudio.google.com. It was being called the "Photoshop killer" since it can very accurately follow your natural language instructions to edit images. Plus it's not bad at generating images either. Planning to have a workflow to demonstrate the power of editing here. I'll have the video up soon. Have you tried using the model yet?

Easily transcribe videos for free using Whisper running in a Docker container and self-hosted n8n. Wrapping the Whisper service in a Docker container makes it easier to maintain by running the container where you want and accessing it directly through the HTTP Request node in n8n. I've setup a simple repository so you can get the service up and running, just check the link above for the repo and the completed workflow. Docker: https://www.docker.com/ Repo with Docker image: https://github.com/jaypetersdotdev/local-whisper You can download the github repository from the link above. Navigate to the folder "local-whisper". Run this command to build the container: docker build -t whisper-api . Then run this command to start the Docker container: docker run -p 5001:5001 whisper-api