GPT-Realtime-Whisper
Streaming speech-to-text model for realtime transcription
A streaming speech-to-text model for low-latency realtime transcription of live audio.

Pricing
Official site · Nov 1, 2026, 6:30 AM
Per minute
$0.017
Realtime audio duration pricing: $0.017 per minute.
OpenAI's official model documentation identifies GPT-Realtime-Whisper as realtime streaming speech-to-text priced by audio duration and explicitly lists $0.017 per minute.
Model Intelligence
Context window
16,000 tokens
Benchmarkable
Yes
Model level
release
Recent stories
1 linked story