AI Video Narration Generator with GPT Vision and TTS

This n8n template automatically narrates any video by extracting key frames, feeding them to a multimodal GPT model to write a natural-sounding script, and then converting that script into a voiceover clip using OpenAI's text-to-speech API. Inspired by OpenAI's own cookbook example, it is ideal for content creators, educators, and marketers who need quick voiceovers for product demos, tutorials, or silent footage without recording their own narration or hiring a voice artist. The whole process, from raw video to finished audio, runs automatically, turning hours of manual scripting and recording into a few minutes of workflow time.

Category: Image & Video Generation