模型广场

GPT-4o Mini Transcribe is OpenAI's smaller, cost-efficient speech-to-text model built on GPT-4o Mini audio capabilities.

上下文

131K

输入 / 1M tokens

-

输出 / 1M tokens

-

缓存读 / 1M

-

缓存写 / 1M

-

GPT-4o Transcribe is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities.

上下文

131K

输入 / 1M tokens

-

输出 / 1M tokens

-

缓存读 / 1M

-

缓存写 / 1M

-

GPT-4o Transcribe Diarize is an automatic speech recognition (ASR) model with built-in speaker diarization, meaning it associates audio segments with different speakers in a conversation.

上下文

131K

输入 / 1M tokens

-

输出 / 1M tokens

-

缓存读 / 1M

-

缓存写 / 1M

-

GPT-5.5 natively supports video comprehension, speech emotion recognition, and autonomous tool calling, delivering omni-modal foundational capabilities for agent-based execution of complex tasks.

上下文

1.1M

输入 / 1M tokens

$10

输出 / 1M tokens

$45

缓存读 / 1M

$1

缓存写 / 1M

$0

Whisper is OpenAI's open-source automatic speech recognition model. It supports transcription and translation across 50+ languages from audio files up to 25 MB. Accepts formats including mp3, mp4, wav, and webm.

上下文

待核

输入 / 1M tokens

-

输出 / 1M tokens

-

缓存读 / 1M

-

缓存写 / 1M

-