У нас вы можете посмотреть бесплатно MiniMe — My AI Digital Doppelgänger или скачать в максимальном доступном качестве, видео которое было загружено на ютуб. Для загрузки выберите вариант из формы ниже:
Если кнопки скачивания не
загрузились
НАЖМИТЕ ЗДЕСЬ или обновите страницу
Если возникают проблемы со скачиванием видео, пожалуйста напишите в поддержку по адресу внизу
страницы.
Спасибо за использование сервиса ClipSaver.ru
The final version of my digital doppelgänger project, made as small as I can, and put in a box. Using a tiny Seeed Studios XIAO ESP32S3 microcontroller, this gadget records my voice, uploads it to the OpenAI speech-to-text converter, feeds the text to a tuned version of ChatGPT through a RAG layer that fills in some of my biographical details using a simple keyword-based database, and passes the response from ChatGPT to the ElevenLabs text-to-speech converter, using a cloned version of my voice. Worth noting that the C++ sketch that makes all this work was largely also written by ChatGPT — my coding skills would never have been up to it. It even came up with quite a lot of the ideas for realising this idea, like using a RAG layer to introduce biographical information. Oh, and ChatGPT also provided the CAD model for the box, which I had 3D printed, based on my simple verbal description of what I needed. Just a taste of what AI may have to offer in the coming years! If you want to build your own version of this project, the hardware design and code is freely available here: https://github.com/astromikemerri/XIA... (Final video edited to remove some of the pauses waiting for a response.)