GPT-4O-TRANSCRIBE-DIARIZE
GPT-4O-TRANSCRIBE-DIARIZE, built by OpenAI, is a chat model capable of speech-to-text and text generation, among other functions, with a notable technical trait of having a large context window of 128,000 tokens. It is genuinely best at processing and transcribing audio inputs, leveraging its speech-to-text capability to generate text from spoken language.
Input
Output
Context
128K
Max Output
2K
Parameters
-
Technical Specifications
Model TypeAudio
Context Window128,000 tokens
Max Output Tokens2,000 tokens
ParametersNot available
Release DateJun 24, 2025
Training CutoffNot available
Licenseproprietary
Open SourceNo
Input Modalities
Audio
Output Modalities
Text
Capabilities
Resources & Links
proprietary, Proprietary - API access only
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.