How to build a Jarvis like super interactive AI that can listen, watch and talk back? We rebuilt the Gemini demo with GPT4V + Whisper + TTS, here is how it really performed…

Build AI powered ad assets at scale with Hubspot campaign assistant for free: https://www.hubspot.com/campaign-assi...


🔗 Links
- Follow me on twitter:   / jasonzhou1993  
- Join my AI email list: https://crafters.ai/
- My discord:   / discord  
- Github - Gemini demo with GPT4V: https://www.crafters.ai/aitools/rebui...


⏱️ Timestamps
0:00 Quick demo
1:41 Project plan & challenges
3:11 Open source Gemini demo & overview
9:37 Project setup
11:22 Setup video recorder
14:37 Setup silence aware audio recorder
16:36 Create img grid
19:44 Whisper
24:31 Connect to GPT4V
27:36 Streaming result & TTS
29:19 Demo


👋🏻 About Me
My name is Jason Zhou, a product designer who shares interesting AI experiments & products. Email me if you need help building AI apps! [email protected]

#gpt4v #gemini #autogen #gpt4 #autogpt #ai #artificialintelligence #tutorial #stepbystep #openai #llm #chatgpt #largelanguagemodels #largelanguagemodel #bestaiagent #chatgpt #agentgpt #agent #babyagi