gpt-4o-transcribe

2025-03-20
Audio
By OpenAI

Input: ￥48.00 / M tokens Output: ￥192.00 / M tokens
Features: Audio Input, Text Output

Input: ￥48.00 / M tokens Output: ￥192.00 / M tokens
Features: Audio Input, Text Output

Model Description

GPT-4o Transcribe is a speech-to-text model that uses GPT-4o 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.

Recommend Models

gpt-4o-image

Image, Vision
Reverse Source

Using reverse engineering to call the model within the official application and convert it into an API.

2025-03-20

Chat, Reasoning, Vision
OpenAI

Our most powerful reasoning model with leading performance on coding, math, science, and vision

2025-04-16

QwQ-32B

Chat, Reasoning
Qwen

QwQ-32B is a 32.5B-parameter reasoning model in the Qwen series, featuring advanced architecture and 131K-token context length, designed to outperform state-of-the-art models like DeepSeek-R1 in complex tasks.

2025-03-06