Model launches

OpenAI has made new real-time voice models available in the Realtime API

OpenAI introduced its new voice models in the Realtime API: GPT-Realtime-2 for voice-based agents, GPT-Realtime-Translate for real-time translation with more than 70 input and 13 output languages, and GPT-Realtime-Whisper for real-time transcription.

OpenAI introduced its new voice models in the Realtime API: GPT-Realtime-2 for voice-based agents, GPT-Realtime-Translate for real-time translation with more than 70 input and 13 output languages, and GPT-Realtime-Whisper for real-time transcription. The service is now available, enabling faster multilingual communication and real-time transcription.