🚀 We tested @openai's new gpt-realtime early – our initial takeaways: Overall a great leap forward in terms of instruction following - the biggest pain point of the Open AI realtime models to date. What else stands out to us: --> Better function calling precision --> Improved comprehension with non-verbal cue detection --> Seamless language switching mid-conversation: IMO the biggest win – a lot of voice architectures struggle with this the most bc of bigger latency on the TTS-side – the sub 500ms end to end latency is impressive here. --> AND: SIP (telephony) support! AND we have added it to our benchmarks! 𝗯𝗲𝗻𝗰𝗵𝗺𝗮𝗿𝗸𝘀 . 𝗰𝗼𝘃𝗮𝗹 . 𝗮𝗶 Instruction following benchmarks coming soon! Tip: Open AI realtime can be used for TTS, STT or turn taking, and you can pair it with other models. Can't wait to see how this transforms voice agents in production environments!