Final narration was synthesized locally using: Kokoro 0.9.4 — https://github.com/hexgrad/kokoro Model: hexgrad/Kokoro-82M v1.0 — https://huggingface.co/hexgrad/Kokoro-82M Generic supplied model voice: af_heart License identified by the creators: Apache License, Version 2.0 https://www.apache.org/licenses/LICENSE-2.0 The model card explicitly describes production deployment of the Apache-licensed weights. No real-person voice sample was supplied and no voice clone was created for this demo. The generated voice is disclosed in the video, preview and transcript. The delivery archive contains generated media and handoff documents, not model weights or library code.