GPT-Realtime-2, Translate, and Whisper

Three new realtime audio models in the API for voice agents that reason, translate, and transcribe live.

GPT-Realtime-2 is OpenAI's first Realtime voice model with GPT-5-class reasoning, improved tool use, recovery behavior, and tone control mid-conversation.
GPT-Realtime-Translate translates speech from 70+ input languages into 13 output languages while keeping pace with the speaker.
GPT-Realtime-Whisper is a streaming speech-to-text model for live transcription.
Pricing: GPT-Realtime-2 is $32 per 1M audio input tokens ($0.40 cached) and $64 per 1M audio output tokens. GPT-Realtime-Translate is $0.034 per minute. GPT-Realtime-Whisper is $0.017 per minute.
Available now in the Realtime API and the developer Playground.

Voice agents that need to reason, translate across languages, or transcribe speech live over the Realtime API.

Existing voice products hitting limits of older Realtime models on tool use, recovery, or live multilingual translation.

Developers shipping voice agents for support, scheduling, dubbing, or transcription who need GPT-5-class reasoning with low latency.

Staying informed is great. Staying ahead is better.

Pick a topic and leave with something you created.

Get new module drops and weekly AI strategy.