GPT Realtime Whisper

Streaming speech-to-text model for low-latency transcript deltas from live audio

BENCHMARKS

Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.

RELEASE DATEMay 7, 2026
WEIGHTSClosed weights
CONTEXT WINDOWNot listed
MAX OUTPUT0
REASONINGNo
TOOL CALLINGNo
INPUTSaudio
OUTPUTStext

Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.