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.

🚀 @Helicone_ai (YC W23) is now the first observability platform to support OpenAI's Realtime API! Integration is just 2 lines of code - update your base URL and add a header. It couldn't be easier. 🔥

Justin Torre

4,094 subscribers

12,150 views • 1 year ago •via X (Twitter)

Science & Technology News & Politics Education

Anya Rossi• Live Now

Private livecam show

8 Comments

Justin Torre1 year ago

Already powering @QAWolfHQ's AI agents that speed up Playwright testing by 5x. "Helicone leads with their Realtime API session view. Setup was minimal, and the logs are beautifully presented." -Nishant Shukla, QAWolf

Justin Torre1 year ago

What this means for you: - Full conversation visibility - Performance metrics for speech-to-speech - 2-line integration with existing setup - Store and replay audio conversations

Justin Torre1 year ago

Huge shoutout to @TinoGuo (our amazing founding engineer) who built this solution in record time. Check out our docs below to get started 👇

Asuka🎀Redpanda1 year ago

@helicone_ai @OpenAI cool

Derek1 year ago

@helicone_ai @OpenAI How is this different from @livekit?

Justin Torre1 year ago

@helicone_ai @OpenAI @livekit Not sure - we do mainly focus on observability though

Antaripa Saha1 year ago

@helicone_ai @OpenAI nicely done, need to try it

RTTS2 years ago

API testing of interfaces is critical to determine if they meet requirements for functionality, reliability, performance, and security. Check out RTTS - the automated testing experts since 1996. #API #testautomation #integrationtest

Related Videos

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

523,556 views • 1 year ago

Built a "YouTube realtime copilot" browser extension using OpenAI's realtime 2 API: The agent watches the video alongside you, and can answer any question you have about what was just said via realtime voice chat. The crazy part to me is: It can differentiate the YouTube's audio stream and your voice, so it doesn't confuse the video as commands, and stays silent unless you ask something!

Built a "YouTube realtime copilot" browser extension using OpenAI's realtime 2 API: The agent watches the video alongside you, and can answer any question you have about what was just said via realtime voice chat. The crazy part to me is: It can differentiate the YouTube's audio stream and your voice, so it doesn't confuse the video as commands, and stays silent unless you ask something!

Zara Zhang

45,631 views • 4 months ago

🎉🚀 Introducing Noya (YC W23) 🚀🎉 Noya is a wireframing tool that generates designs & code. Try it out: Noya lets you work in low-fidelity wireframes, while still producing high-fidelity designs and React prototypes to share with your team.

🎉🚀 Introducing Noya (YC W23) 🚀🎉 Noya is a wireframing tool that generates designs & code. Try it out: Noya lets you work in low-fidelity wireframes, while still producing high-fidelity designs and React prototypes to share with your team.

Devin Abbott

108,304 views • 3 years ago

We just launched Onchain – the first x402 payments aggregator. Add crypto payments to your API in 3 lines of code. Automatic routing across multiple facilitators. Zero blockchain knowledge required. Starting with Base coverage from day one. Here's how it works.. 1/10 🧵

We just launched Onchain – the first x402 payments aggregator. Add crypto payments to your API in 3 lines of code. Automatic routing across multiple facilitators. Zero blockchain knowledge required. Starting with Base coverage from day one. Here's how it works.. 1/10 🧵

Vesper

25,347 views • 10 months ago

Native x402 support just landed in the CDP SDK. 🚀 Add x402 payments to your app, or spin up x402-gated endpoints, in 3 lines of code. Coinbase handles wallets, multi-chain support, and facilitator auth, all in a single SDK. ↓

Native x402 support just landed in the CDP SDK. 🚀 Add x402 payments to your app, or spin up x402-gated endpoints, in 3 lines of code. Coinbase handles wallets, multi-chain support, and facilitator auth, all in a single SDK. ↓

Coinbase Developer Platform🛡️

17,591 views • 2 months ago

The first bug bounty platform to be integrated into Caido🚀 New plugin "YesWeCaido" by YesWeHack ⠵ is out now in the Caido Store. Fetch all of your bug bounty programs on YesWeHack and pick scopes to add to your Caido instance directly. Check out more details:

The first bug bounty platform to be integrated into Caido🚀 New plugin "YesWeCaido" by YesWeHack ⠵ is out now in the Caido Store. Fetch all of your bug bounty programs on YesWeHack and pick scopes to add to your Caido instance directly. Check out more details:

Caido

18,573 views • 1 year ago

🚀 is LIVE! 🎉 We’re thrilled to announce that is officially live, and the first 4 presales (ICOs) are now listed! 🌟 Over the coming days, we’ll be rolling out all the functionalities of the platform to give you the best experience possible. Stay tuned—this is just the beginning! 🙏 Thank you for your support. Together, we’ll ride the new wave of ICOs to success! 👉 Check out the platform now:

🚀 is LIVE! 🎉 We’re thrilled to announce that is officially live, and the first 4 presales (ICOs) are now listed! 🌟 Over the coming days, we’ll be rolling out all the functionalities of the platform to give you the best experience possible. Stay tuned—this is just the beginning! 🙏 Thank you for your support. Together, we’ll ride the new wave of ICOs to success! 👉 Check out the platform now:

Asvoria $ASV/SOL

12,566 views • 1 year ago

Nano Banana Lite is fast! 🍌🚀 I put it to the test with the Interactions API and Gemini Live to illustrate stories in near-realtime 🤯👇 Try it out now 👉

Nano Banana Lite is fast! 🍌🚀 I put it to the test with the Interactions API and Gemini Live to illustrate stories in near-realtime 🤯👇 Try it out now 👉

Thor 雷神 ⚡️

13,657 views • 2 months ago

This is crazy, I can talk to OpenAI's realtime API, and it'll respond back with voice, and then help call Codex to help me code! Got curious about Codex and its realtime integration, and found codex's feature flag `realtime_conversation` integrated for the codex app-server. How it works: - launch codex app-server with realtime - connect a client to realtime through WebRTC voice connection - Codex app-server is also attached on the side - talk to realtime - realtime decides whether coding is needed, and responds back with events - Codex app-server takes these events and runs codex agent turns - codex writes code like your codex cli exp Keep in mind OpenAI hasn't released this officially, they're still actively working on it, I just created a fork. This is a completely new UX than the usual chat interface for agentic coding. For example, when the agent responds back in voice, it's actually faster for me to read the response, and I don't actually find voice response that useful unless it does so in the background. But image realtime working in the background, you can talk to it, realtime keeps track of the different agents working on your tasks and your status. More to come on demo side, i'll make a more polished version and include voice, but thought this was cool to share. You can see in the responses the distinction between my voice input, realtime response, and realtime calling Codex to do work!

This is crazy, I can talk to OpenAI's realtime API, and it'll respond back with voice, and then help call Codex to help me code! Got curious about Codex and its realtime integration, and found codex's feature flag `realtime_conversation` integrated for the codex app-server. How it works: - launch codex app-server with realtime - connect a client to realtime through WebRTC voice connection - Codex app-server is also attached on the side - talk to realtime - realtime decides whether coding is needed, and responds back with events - Codex app-server takes these events and runs codex agent turns - codex writes code like your codex cli exp Keep in mind OpenAI hasn't released this officially, they're still actively working on it, I just created a fork. This is a completely new UX than the usual chat interface for agentic coding. For example, when the agent responds back in voice, it's actually faster for me to read the response, and I don't actually find voice response that useful unless it does so in the background. But image realtime working in the background, you can talk to it, realtime keeps track of the different agents working on your tasks and your status. More to come on demo side, i'll make a more polished version and include voice, but thought this was cool to share. You can see in the responses the distinction between my voice input, realtime response, and realtime calling Codex to do work!

Matthew Lam

17,674 views • 4 months ago

Ready for 800 million Telegram users? JoyID Passkey Wallet has developed a unique Telegram bot and miniapp SDK that enables seamless multi-chain integration. With just 10 lines of code, any dApp can now connect to the Telegram ecosystem and tap into its vast user base. 🚀 #Telegram #PasskeyWallet #miniapp

Ready for 800 million Telegram users? JoyID Passkey Wallet has developed a unique Telegram bot and miniapp SDK that enables seamless multi-chain integration. With just 10 lines of code, any dApp can now connect to the Telegram ecosystem and tap into its vast user base. 🚀 #Telegram #PasskeyWallet #miniapp

cipher

12,851 views • 2 years ago

🧭nCompass (YC W24) is a platform for simplified hosting & acceleration of open-source LLMs. Its API requires only one line of code to integrate low-latency versions of these models into your AI pipeline. Congrats on the launch Aditya Rajagopal & Diederik Adriaan Vink!

🧭nCompass (YC W24) is a platform for simplified hosting & acceleration of open-source LLMs. Its API requires only one line of code to integrate low-latency versions of these models into your AI pipeline. Congrats on the launch Aditya Rajagopal & Diederik Adriaan Vink!

Y Combinator

10,741 views • 2 years ago

evaluate now supports @Base 🔵 with our evaluateSDK - a flexible SDK that instantly adds live chat and item swapping to onchain projects. Want to add social trading to your app, marketplace, or game? The evaluate SDK enables this in just a few lines of code.

evaluate now supports @Base 🔵 with our evaluateSDK - a flexible SDK that instantly adds live chat and item swapping to onchain projects. Want to add social trading to your app, marketplace, or game? The evaluate SDK enables this in just a few lines of code.

evaluate

32,934 views • 2 years ago

You can now add Claude Code to any vibe coded app. We just launched the new Claude Code integration on vibecode.dev. Which allows you to build fully Agentic Applications. In a single prompt, with no API Key. Here's is an example and tutorial: 0:00 - Claude Code for Twitter Example 01:52 - Building the Claude Code for Motion Graphics

You can now add Claude Code to any vibe coded app. We just launched the new Claude Code integration on vibecode.dev. Which allows you to build fully Agentic Applications. In a single prompt, with no API Key. Here's is an example and tutorial: 0:00 - Claude Code for Twitter Example 01:52 - Building the Claude Code for Motion Graphics

Riley Brown

30,119 views • 7 months ago