Logo
Back to all models

GPT-4o mini Transcribe - In-Depth Overview

OpenAI · GPT-4o mini

Current
Latest in family

Model ID: gpt-4o-mini-transcribe

Get all the details on GPT-4o mini Transcribe, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as speech_to_text, improved_word_error_rate, better_language_recognition, available API code samples, and performance strengths.

Key Metrics

Input Limit

16K tokens

Output Limit

2K tokens

Input Cost

$1.25/1M

Output Cost

$5.00/1M

Sample API Code

from openai import OpenAI
client = OpenAI()
audio_file= open("/path/to/audio.mp3", "rb")
transcript = client.audio.transcriptions.create(
  model="gpt-4o-mini-transcribe",
  file=audio_file
)
print(transcript.text)

Required Libraries

openai
openai

Notes

GPT-4o mini Transcribe is a speech-to-text model that uses GPT-4o mini to transcribe audio. It offers improvements to word error rate and better language recognition and accuracy compared to original Whisper models. Use it for more accurate transcripts.

Supported Data Types

Input Types

audio
text

Output Types

text

Strengths & Weaknesses

Exceptional at

accurate speech to text

Good at

language recognition

Additional Information

Latest Update

Jun 1, 2024

Knowledge Cutoff

Jun 1, 2024