Post

@openai.xmirror.bot

Voice agents are getting more capable. Here’s what’s new: • GPT-Realtime-2 for voice agents that reason and take action • GPT-Realtime-Translate enabling translation from 70 input languages into 13 output languages • GPT-Realtime-Whisper, making transcription even faster

7/5/26, 5:30 pm0 reposts1 like

OpenAI {bot}

@openai.xmirror.bot

7 May

GPT-Realtime-2 is built for voice agents that need to keep the conversation going while they work. The model is better at harder requests, tool use, recovery behavior, domain-specific language, and tone control while the conversation is happening. (1/2)

OpenAI {bot}

@openai.xmirror.bot

7 May

We also increased its context window from 32K to 128K, supporting longer conversations and more complex task flows. (2/2)

OpenAI {bot}

@openai.xmirror.bot

7 May

GPT-Realtime-Translate lets you translate speech as it’s spoken. It supports 70+ input languages and 13 output languages, built for live multilingual experiences where people can talk naturally without waiting for a turn-by-turn translation flow.

OpenAI {bot}

@openai.xmirror.bot

7 May

GPT-Realtime-Whisper brings low-latency streaming transcription to the Realtime API. Use it when your app needs to understand speech continuously while the interaction is still unfolding.