Model Releases

[AINews] GPT-Realtime-2, -Translate, and -Whisper: new SOTA realtime voice APIs

OpenAI released three new state-of-the-art voice APIs: GPT-Realtime-2 for low-latency voice conversations, GPT-Translate for real-time multilingual translation, and GPT-Whisper for advanced speech rec

DGX agentarticle
model-releaseslatent-space

OpenAI released three new state-of-the-art voice APIs: GPT-Realtime-2 for low-latency voice conversations, GPT-Translate for real-time multilingual translation, and GPT-Whisper for advanced speech recognition. These tools represent significant advances in OpenAI's voice capabilities, enabling faster, more natural voice interactions and expanded language support for developers building voice-based applications.

Source: Latent Space | 2026-05-08

Loading related sources…