Hello! I am JM, the creator of TalkPersona. This project is aimed at developing a unique AI companion with real-time video (talking face) and natural voice capabilities, that you won't see in any other public spaces. A few years ago, I wanted to create a virtual psychologist, something more advanced than the 1960s ELIZA. Then with the advent of large language models, I thought, why not use them for more general and customizable purposes? Adding some talking faces and natural voices came later, along with my careful customization to make it truly unique. That’s how TalkPersona has evolved into its current form.
This artificial intelligence chatbot is computationally intensive, as it includes quite a few neural networks, including an LLM (large language model) which is self-run (not relying on external APIs) and allows context (AI companion's role, background of chat) to be set, transcription, text to speech, wave file pattern extraction, and face animation with lip sync. There might be some initial latency when the AI chatbot starts talking in video, but it should smooth out after two seconds. You have the option to disable video so AI replies with voice-only if you want an even faster response. The speed experience may differ depending on where you are located.
As it requires quite some compute, I'm only running one free AI video chatbot at selected times for the moment. It can be scaled up to multiple chatbots if there is demand and enough donations supporting it. Feel free to leave me a feedback. You can also reach me by emailing me at: [email protected]
If you enjoyed the video chat with AI or simply wish to support the development effort, please consider donating here, any amount is appreciated! You can also provide a link back to TalkPersona by embedding the following HTML codes into your website:
<a href="https://talkpersona.com">TalkPersona videobot - free live AI Video Chatbot as an AI Companion, with realistic talking face and natural voice</a>