GPT-Realtime-Translate
Streaming speech-to-speech translation model for live multilingual audio
- Context window
- 16K tokens in · 2K out
BENCHMARKS
Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.
OpenAI's past year
23 release days in the past year, about one every 16 days. The next is expected around Nov 5, 2026. Forecasts ↗
NovDecJanFebMarAprMayJunJulAugSepOctNov
Specifications
RELEASE DATEMay 7, 2026
WEIGHTSClosed weights
CONTEXT WINDOW16K
MAX OUTPUT2K
REASONINGNot listed
TOOL CALLINGNot listed
INPUTSaudio/pcm
OUTPUTStext, audio/pcm
Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.