Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

You can build interactive applications with gpt-realtime-1.5, so users can control app state more naturally with voice. Hi Chappy 👋

OpenAI Developers

372,860 subscribers

1,837,415 views • 2 months ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Here’s how you can integrate GPT-Realtime-2 to bring voice control to a CRM workflow.

Here’s how you can integrate GPT-Realtime-2 to bring voice control to a CRM workflow.

OpenAI Developers

153,798 views • 2 months ago

Voice workflows just got stronger with gpt-realtime-1.5 in the Realtime API. The model offers more reliable instruction following, tool calling, and multilingual accuracy. Demo with Charlie Guo

Voice workflows just got stronger with gpt-realtime-1.5 in the Realtime API. The model offers more reliable instruction following, tool calling, and multilingual accuracy. Demo with Charlie Guo

OpenAI Developers

417,671 views • 4 months ago

Here’s how we built a restaurant voice agent using gpt-realtime-1.5

Here’s how we built a restaurant voice agent using gpt-realtime-1.5

OpenAI Developers

86,962 views • 4 months ago

With GitHub Spark, you can build personal, AI-assisted applications. ✨ Watch how we created a travel log app in minutes. 👀

With GitHub Spark, you can build personal, AI-assisted applications. ✨ Watch how we created a travel log app in minutes. 👀

GitHub

101,730 views • 1 year ago

When your voice agent debugs your slides live Charlie Guo is using gpt-realtime-1.5

When your voice agent debugs your slides live Charlie Guo is using gpt-realtime-1.5

OpenAI Developers

242,373 views • 3 months ago

Voice mode in Comet uses OpenAI Developers’s new gpt-realtime-1.5. With this upgrade we were able to optimize tool call stability by over 25%, and dramatically improve voice expressiveness.

Voice mode in Comet uses OpenAI Developers’s new gpt-realtime-1.5. With this upgrade we were able to optimize tool call stability by over 25%, and dramatically improve voice expressiveness.

Comet

54,538 views • 4 months ago

You can build a coding agent in 20 seconds with gpt-5.3-codex-spark

You can build a coding agent in 20 seconds with gpt-5.3-codex-spark

Nick

33,072 views • 4 months ago

GPT-5 just dropped in Azure AI Foundry. Devs can tap into the full suite of GPT-5 models with a single endpoint using Foundry’s AI-powered model router. Intelligent model selection, so you can build with ease.

GPT-5 just dropped in Azure AI Foundry. Devs can tap into the full suite of GPT-5 models with a single endpoint using Foundry’s AI-powered model router. Intelligent model selection, so you can build with ease.

Microsoft Azure

18,859,065 views • 11 months ago

That’s it. That’s the tweet. The Realtime API now supports WebRTC—you can add Realtime capabilities with just a handful of lines of code. We’ve also cut prices by 60%, added GPT-4o mini (10x cheaper than previous prices), improved voice quality, and made inputs more reliable.

That’s it. That’s the tweet. The Realtime API now supports WebRTC—you can add Realtime capabilities with just a handful of lines of code. We’ve also cut prices by 60%, added GPT-4o mini (10x cheaper than previous prices), improved voice quality, and made inputs more reliable.

OpenAI Developers

523,494 views • 1 year ago

GPT-5 just dropped in Azure AI Foundry. Devs can tap into the full suite of GPT-5 models with a single endpoint using Foundry’s AI-powered model router. Intelligent model selection, so you can build with ease. Start Building:

GPT-5 just dropped in Azure AI Foundry. Devs can tap into the full suite of GPT-5 models with a single endpoint using Foundry’s AI-powered model router. Intelligent model selection, so you can build with ease. Start Building:

Microsoft Azure

81,959 views • 11 months ago

Want to build a SaaS app where users can have custom domains? Learn how you can use Next.js to handle subdomains (leerob.acme.com) with our updated starter template and guide.

Want to build a SaaS app where users can have custom domains? Learn how you can use Next.js to handle subdomains (leerob.acme.com) with our updated starter template and guide.

Lee Robinson

104,963 views • 1 year ago

At OpenAI DevDay, we introduced the Realtime API with a demo of an interactive solar system you can navigate with your voice. A lot of you have asked how it was built, so we've open-sourced it—with a twist: this version uses our new WebRTC integration. Have fun exploring! 🌍

At OpenAI DevDay, we introduced the Realtime API with a demo of an interactive solar system you can navigate with your voice. A lot of you have asked how it was built, so we've open-sourced it—with a twist: this version uses our new WebRTC integration. Have fun exploring! 🌍

Katia Gil Guzman

316,548 views • 1 year ago

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.

OpenAI

3,644,441 views • 2 months ago

AI agents continue to amaze… My GPT-4 coding assistant learned how to build apps with *authenticated* users! It can now: - build and design a web app - create a backend with working db - handle auth - upload code to GitHub - deploy to Vercel Things are starting to get crazy!

AI agents continue to amaze… My GPT-4 coding assistant learned how to build apps with authenticated users! It can now: - build and design a web app - create a backend with working db - handle auth - upload code to GitHub - deploy to Vercel Things are starting to get crazy!

Mckay Wrigley

512,415 views • 3 years ago

🚀 Launching Pacific Alpha Mainnet Users worldwide can now interact with the modular EVM L2 for ZK-enabled applications. Learn More:

🚀 Launching Pacific Alpha Mainnet Users worldwide can now interact with the modular EVM L2 for ZK-enabled applications. Learn More:

Manta Network (🔱,🔱)

375,570 views • 2 years ago

Watch me control my computer with just my voice. This is the future of operating systems. No hands. GPT-Realtime 2.0 is very, very underrated. Demo:

Watch me control my computer with just my voice. This is the future of operating systems. No hands. GPT-Realtime 2.0 is very, very underrated. Demo:

Farza 🇵🇰🇺🇸

3,769,794 views • 1 month ago

why build on cloudflare sandboxes? <50 lines of code gives you: - interactive access to parallel bash sessions - built-in replays so you can reload and not lose state - durable objects to handle real-time sync all day kate and I had so much fun with this 🎉 so can you!

why build on cloudflare sandboxes? <50 lines of code gives you: - interactive access to parallel bash sessions - built-in replays so you can reload and not lose state - durable objects to handle real-time sync all day kate and I had so much fun with this 🎉 so can you!

Naresh 🍓

35,472 views • 5 months ago

Say .hi to your new web3 identity 👋 Together with hi | Web 3 Neo-Banking, we’re launching a .hi brand Web3 TLD and a custom UD debit Mastercard. 🚀 Verified hi users can now claim .hi domains matching their account username, for free! Learn more:

Unstoppable Domains

84,370 views • 3 years ago

This is just insane… My GPT-4 coding assistant can now: - build and design a frontend - create a backend with working db - correctly hook them up - upload code to GitHub - deploy it to Vercel I can now build *complete* apps with nothing more than my voice. The future is here!

This is just insane… My GPT-4 coding assistant can now: - build and design a frontend - create a backend with working db - correctly hook them up - upload code to GitHub - deploy it to Vercel I can now build complete apps with nothing more than my voice. The future is here!

Mckay Wrigley

5,715,535 views • 3 years ago