gpt-4o-transcribe

模型描述

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.

全文结束

推荐模型

gpt-4.1-nano-2025-04-14

GPT-4.1 nano 是最快、最具性价比的 GPT-4.1 模型。

gemini-2.5-flash-preview-04-17

Gemini-2.5-Flash-Preview-04-17 is a large language model supporting text, image, video, and audio inputs, with advanced output and code execution capabilities and high token limits.

o4-mini

Our faster, cost-efficient reasoning model delivering strong performance on math, coding and vision