Sobre

I’m looking for a qualified automation developer to build a hands-off workflow that automatically creates videos from curated image and text data. The goal is to go from a folder or CSV of photos and short captions → to a finished video with AI voiceover, captions, and upload to platform. This is not a manual editing job — it requires automation logic (n8n, Python, or FFmpeg scripting). What the Automation Should Do Scrape or Pull Images: Fetch 100–120 public-domain photos from online sources (Wikimedia, Picryl, Flickr Commons, etc.) Extract the photo title/description and save it in a CSV or JSON. Generate Voiceovers: Send each caption to an AI voice tool ( via API) and save MP3 files. Assemble the Video: Combine each image with its corresponding audio + caption text. Add light panning/zoom effects, a film-grain overlay, and background ambiance. Output a 1080p MP4. Automation Control: Build this as a single-click or scheduled workflow in n8n (preferred) or Python. Include an editable config for the search keywords, audio voice, and output folder.