GPT-Transcribe
Latest GPT-TranscribeHigh-accuracy speech-to-text model for audio files and committed Realtime turns
- Since the last one
- 495 days after GPT-4o Transcribe
Since GPT-4o Transcribe
2 releases in the GPT-Transcribe line.
Released495 days later
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 DATEJul 28, 2026
WEIGHTSClosed weights
CONTEXT WINDOWNot listed
MAX OUTPUT0
REASONINGNot listed
TOOL CALLINGNot listed
INPUTStext, audio/flac, audio/mpeg, audio/mp4, audio/ogg, audio/wav, audio/webm, audio/pcm, audio/pcmu, audio/pcma
OUTPUTStext
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.