You can run a transcription model and a language model (the AI you talk to) locally however you will need a beefy GPU especially if you want to run the large models for better results.
OpenAI’s Whisper is open source and does transcription, and you can run inference on language models like LLaMa (+variants) or GPT4all locally. To store information long term (“AI memory”) you could find an open source vector database but I don’t have experience with this.
I believe this is what’s happening in your reference clip. The reason the camera shake looks like it’s synchronized to the music is because the speed ramps up on every beat, causing the camera shake to be more pronounced each beat
If you added the shake after the speed ramping the “intensity” (really frequency) of the motion would remain constant and it wouldn’t look like the reference video
This is a camera shake effect that has been added before the speed ramping. Most video editors can do this effect:
LLaMa-2 was just released and the fine-tunings people have made of it are topping the leaderboards right now in terms of performance for an open source language model. As for inference, don’t forget to look into quantization so you can run larger models on limited vram. I’ve heard about vLLM and llama.cpp and its derivatives.
If you’re looking for a GPU ~$300, I heard a used 3060 is better value than a 4060 right now on performance and memory throughout but not power efficiency (if you want an easy time with ML unfortunately the only option is nvidia).
Good luck! Would be nice to get an update if you find a good solution, it seems could share your use case