DataLearner logoDataLearnerAI
Latest AI Insights
Model Leaderboards
Benchmarks
Model Directory
Model Comparison
Resource Center
Tools
LanguageEnglish
DataLearner logoDataLearner AI

A knowledge platform focused on LLM benchmarking, datasets, and practical instruction with continuously updated capability maps.

Products

  • Leaderboards
  • Model comparison
  • Datasets

Resources

  • Tutorials
  • Editorial
  • Tool directory

Company

  • About
  • Privacy policy
  • Data methodology
  • Contact

© 2026 DataLearner AI. DataLearner curates industry data and case studies so researchers, enterprises, and developers can rely on trustworthy intelligence.

Privacy policyTerms of service
Page navigation
目录
Model cataloggpt-4o-transcribe
GP

gpt-4o-transcribe

语音大模型

GPT-4o-Transcribe

Release date: 2025-03-20更新于: 2025-03-21 10:54:17870
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
4K
Chinese support
Supported
Reasoning ability

GPT-4o-Transcribe is an AI model published by OpenAI, released on 2025-03-20, for 语音大模型, with 0.0B parameters, and 4K tokens context length, requiring about 0 storage, under the 不开源 license.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

gpt-4o-transcribe

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
4K tokens
Max output length
No data
Model type
语音大模型
Release date
2025-03-20
Model file size
0
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
gpt-4o-transcribe

Open source & experience

Code license
不开源
Weights license
不开源- 不开源
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Live demo
https://www.openai.fm/
gpt-4o-transcribe

Official resources

Paper
Introducing next-generation audio models in the API
DataLearnerAI blog
三年后OpenAI再次发布自动语音识别和语音合成大模型(替换Whisper系列):不开源,仅提供API,英文错字率已经下降到2.46%
gpt-4o-transcribe

API details

API speed
No data
No public API pricing yet.
gpt-4o-transcribe

Benchmark Results

No benchmark data to show.
gpt-4o-transcribe

Publisher

OpenAI
OpenAI
View publisher details
GPT-4o-Transcribe

Model Overview

GPT-4o-Transcribe是OpenAI在2025年3月21日发布的自动语音识别的大模型,用于替换2年前OpenAI开源的Whisper系列自动语音识别模型,它是基于GPT-4o架构构建,识别错误率相比此前模型更低,在英文的错字率(word error rate)仅有2.46%。


GPT-4o-Transcribe支持100多种语言的自动语音识别,支持噪音消除和基于语义的语音分割(也就是根据语音的语义来进行语音分割,降低识别错误率)。


GPT-4o-Transcribe在大量的高质量、多样化的语音数据集上训练,引入来强化学习和midtraining技术来处理具有挑战性的场景。


GPT-4o-Transcribe不开源,目前仅通过API提供,每100万语音输入的tokens需要6美元(大约一分钟0.006分钱)。

DataLearner 官方微信

欢迎关注 DataLearner 官方微信,获得最新 AI 技术推送

DataLearner 官方微信二维码