Face Studio — RobotCandy Lab, 21 October 2026 Characters: Ada, Bruce and Bo from CreateGameCharacters' MetaHuman-to-GLB sample gallery, revision 5faa13fbfccefb3a194943433f6dd42ef6195d00. https://github.com/creategamecharacters/metahuman-to-glb https://creategamecharacters.com The upstream repository is MIT licensed. Its full licence is included in UPSTREAM-LICENSE.txt. Hair atlas interpretation and legacy eye reconstruction were adapted from that project's viewer. Character geometry and textures are repacked for browser use; the original authors retain their rights. MetaHuman is Epic Games technology. These samples are not CC0 or a claim of RobotCandy ownership. Epic's applicable Unreal Engine / MetaHuman terms still apply to MetaHuman content: https://www.metahuman.com/license Three.js: MIT, Copyright 2010-2026 three.js authors. https://github.com/mrdoob/three.js/blob/dev/LICENSE Meshoptimizer: MIT, Copyright 2016-2026 Arseny Kapoulkine. https://github.com/zeux/meshoptimizer/blob/master/LICENSE.md glTF Transform: MIT, Copyright 2020-2026 Don McCurdy. https://github.com/donmccurdy/glTF-Transform Speech: the original nine Face Studio recordings were generated with the local Voice CLI on 20 October 2026. EVA: Eleven v3; Garret: Eleven Flash 2.5; Heart: Kokoro 82M. Dialogue is fictional. No real speaker identity is claimed. No live generation is performed by this website. Phoneme timing: facebook/wav2vec2-lv-60-espeak-cv-ft, Apache-2.0; ONNX conversion: onnx-community/wav2vec2-lv-60-espeak-cv-ft-ONNX, revision 0c57084ff1713c6ab2edd62ff710176c705f2a27. The model is used only during offline preparation, not distributed here. https://huggingface.co/facebook/wav2vec2-lv-60-espeak-cv-ft Transcript alignment preparation also uses phonemizer-fork 3.3.2 and eSpeak NG through espeakng-loader 0.2.4. These preparation tools are not distributed in the website. Original acoustic timings remain available for comparison. https://github.com/bootphon/phonemizer https://github.com/thewh1teagle/espeakng-loader Legacy mouth timing: Rhubarb Lip Sync 1.14.0, MIT, Daniel Wolf. https://github.com/DanielSWolf/rhubarb-lip-sync