GPT-4o Transcribe

A powerful speech-to-text model powered by GPT-4o, capable of transcribing and translating audio into text with high accuracy.

Supports a wide range of inputs and outputs, including Text, Image, Video, Audio, Transcription, and Text-to-Speech. Specialized for general-purpose transcription and translation tasks. Supports fine-tuning for custom applications.

Pricing:

• Text tokens: $2.50 per 1M input tokens, $10.00 per 1M output tokens
• Audio tokens: $6.00 per 1M input tokens
• Estimated cost: $0.006 per minute