← Portfolio · P-05
Multimodal AI · Personas
Integrating AI in Recreating Iconic Personalities
A proof-of-concept multimodal experience exploring how a historical figure can be represented through LLM-driven conversation, voice synthesis, and an animated visual presentation.
Personality emulation across text, voice, and avatar layers.
OpenAI-driven personality emulation, ElevenLabs voice synthesis, and a digital portrait combine into a more immersive historical interaction than a text-only chatbot.
OpenAI integration
The assistant was shaped using JFK speeches, interviews, and secondary sources to keep responses historically grounded.
Voice synthesis
ElevenLabs generated speech output matched to the chosen historical figure's recognizable voice.
Avatar layer
A digital portrait added visual presence, expression, and stronger multimodal immersion.
Believability mattered — but so did restraint.
Historical accuracy had to be balanced against the tendency of generative models to hallucinate: a persona that sounds convincingly like JFK is only worth building if it stays grounded in what he actually said. On top of that, integrating the LLM, voice, and animation layers into one coherent interaction introduced meaningful engineering complexity.
The educational use case was the main motivation — making history feel conversational and immediate, without letting the presentation outrun the source material.
