OpenAI
OpenAI: GPT-4o Transcribe
openai/gpt-4o-transcribe
GPT-4o Transcribe is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.
Input
$2.5
/ 1M tokens · Token reference
Output
$10
/ 1M tokens · Token reference
Context window
128K
tokens
Transcription output · Token reference fields do not establish an output-unit price.
Limits
Context
128,000
tokens
Max output
115,200
90% of the context window
Model facts
Author
OpenAI
Tokenizer
GPT
Modality
Audio -> Transcription
Created
Apr 27, 2026
Publication status
Hugging Face: not mappedLicense: not publishedParameter count: not published
Modalities
Input · AudioOutput · Transcription