Using OpenAI’s Advanced Voice Mode in an App (Real-Time API Demo)

[@BrockMesarich]

What are you going to build with the real-time API?
✉ For Business Inquiries: [e-mail]
📈 Join my AI Skool Community: www.skool.com/ai-innovators-circle/about
💼 Connect with me on LinkedIn: www.linkedin.com/in/brock-mesarich-757573265/

[@tommypospa]

Great demo - I wonder which voice platforms have already integrated this..

[@BrockMesarich]

💪🏼

[@syedmraza-ca]

Implementing Voice Mode Manually [STT->LLM->TTS] was a mountain to climb! I'm definitely going to implement the native real-time API so users have an option to use that instead (I think its a lot better!)

[@BrockMesarich]

let me know how it goes!

[@DevPythonUnity]

but it does not sound any different then their normal TTS, it does nto have emotions and capability to change tonality

[@BrockMesarich]

Have you played around with it? It actually does have some cool emotions and tonality

[@libertyIsAll132]

I’d love to run this on my apple watch , with only one tap

[@BrockMesarich]

It will eventually be that accessible!

[@Max12-p]

Do you find its functions shocking to you

[@BrockMesarich]

Yes