OpenAI

GPT-4o Transcribe

Name: OpenAI GPT-4o Transcribe
Author: OpenAI

Compare

Model ID:gpt-4o-transcribe

2024-06-01

Compare

GPT-4o Transcribe is OpenAI's full-featured speech-to-text model, built on the GPT-4o architecture for maximum transcription accuracy. It delivers lower word error rates and superior language recognition compared to both Whisper and GPT-4o Mini Transcribe, making it the best choice for high-accuracy transcription needs. The model supports real-time audio streaming via WebSocket connections, contextual prompts for specialized vocabulary, and log probability outputs for confidence scoring.

API|Proprietary Model

Knowledge Cutoff

2024-06-01

The date this AI finished learning. It may not know about things that happened after this date.

Input → Output Format

The types of content this AI can receive, and what it can produce in return.

Context Memory

—

The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.

Cost/1M Words

$2.5IN$10OUT

The cost of using this AI directly in your own application. Shown in USD per 1 million units of text (tokens).