Can someone provide recommendations for a project I’ve been brainstorming?

I’ve recently wanted to make a small raspberry pi system that will use a speaker/microphone coupled with a sensor/camera and open cv or the equivalent to make a conversing and surrounding-aware robot. I wanted to attach this to a remote control bird, and I was wondering what the best and most inexpensive materials would be for my needs. It’s kinda like a bird that can recognize people and imitate one’s voice using a TTS or other language learning model. Responses could be generated using an API key from ChatGPT. Thanks!