Hi everyone, I've been trying to add text overlay on a video using NCA toolkit, specifically the ffmpeg compose endpoint. I also use the NCA toolkit api GPT and it recommended me to use a filter called "drawtext" but that's not working, it returns an error 500 with the following statements: - Either text, a valid file, a timecode or text source must be provided - Error initializing filters - Failed to set value 'drawtext' for option 'filter_complex': Invalid argument - Error parsing global options: Invalid argument I would really appreciate any help to get this working! Maybe a dedicated endpoint to this as well would be a banger. Thank you.

In this video, I’ll show you exactly how to ditch costly monthly API subscriptions and replace it with one free tool, the No-Code Architect Toolkit. Replace, ChatGPT Whisper, Cloud Convert, Createomate, JSON2Video, PDF(dot)co, Placid, OCodeKit. ----------------- Docker Image → stephengpope/no-code-architects-toolkit:latest Postman Template → https://bit.ly/49Gkh61 NCA Toolkit API GPT → https://bit.ly/4feDDk4 Github Repository → https://bit.ly/3DhFo2A

Hi everyone, I'll do my best to explain. So I have a database of real estate properties, each one ha videos of a house and data like the amount of rooms, bathrooms, etc. I'll feed all that house data into chatgpt so that it can create a video script, and then I'll turn that script into voice with Elevenlabs. After that I want to merge all those video shots of the house into one, for example let's say the scripted voice talks about the kitchen for the first 5 seconds, so the kitchen video and also some text overlay saying "kitchen" would appear in that part. Then for the next video shot, the process would repeat and so on...And the final result would be like a slideshow video showing each parts of the house, with appropriate text overlay on each part, and the elevenlabs voice on top (timed accordingly of course). Is the no code architects tool kit capable of doing this? I really wanna use it haha. And if not what tools would you recommend? Thank you! I would appreciate any help.

Hi everyone, I have multiple talking audio clips and I need to find way to programmatically split them into small clips. Do you know of any tool or API, which could identify gaps inside the talking audio and produce multiple ~1 minute WAV/MP3 files? Use case: These clips are talked by my assistant who is not very good in English, or has a strong accent. I recently found a SieveData API, where AI can help me to dub the video with the same voice, but better English. The problem is that when I upload clips of 8-12 minutes, the result is the audio of the same length, but if algorithm sees it has spoken everything too fast, it will try to slow down the end of the talk. So it sounds a bit weird, when the same person is talking slower at the end. My idea is to split audio into a shorter clips, then process via API, and in this way reduce a risk that the voice will be slower or faster.

It gives me error 404 "The requested URL was not found on the server. If you entered the URL manually please check your spelling and try again." The other endpoints work fine, though.