GPT-4o Transcribe

Automatic Speech Recognition • OpenAI • Proxied

A speech-to-text model that uses GPT-4o to transcribe audio with improved word error rate and better language recognition compared to original Whisper models.

Model Info
Terms and License	link ↗
More information	link ↗

Usage

const response = await env.AI.run(
  'openai/gpt-4o-transcribe',
  {
    file: 'https://cdn.openai.com/API/docs/audio/alloy.wav',
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Input / Output JSON

Input
Output

{
    "file": "https://cdn.openai.com/API/docs/audio/alloy.wav"
}

{
    "text": "The sun rises in the east and sets in the west. This simple fact has been observed by humans for thousands of years."
}

Examples

With Language Hint — Transcribe with a language hint for better accuracy

const response = await env.AI.run(
  'openai/gpt-4o-transcribe',
  {
    file: 'https://cdn.openai.com/API/docs/audio/shimmer.wav',
    language: 'en',
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Input / Output JSON

Input
Output

{
    "file": "https://cdn.openai.com/API/docs/audio/shimmer.wav",
    "language": "en"
}

{
    "text": "The beach was a popular spot on a hot summer day. People were swimming in the ocean, building sandcastles, and playing beach volleyball."
}

Guided Transcription — Use a prompt to guide transcription style and context

const response = await env.AI.run(
  'openai/gpt-4o-transcribe',
  {
    file: 'https://cdn.openai.com/API/docs/audio/fable.wav',
    language: 'en',
    prompt:
      'This is a technical discussion about Kubernetes and cloud-native architecture.',
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Input / Output JSON

Input
Output

{
    "file": "https://cdn.openai.com/API/docs/audio/fable.wav",
    "language": "en",
    "prompt": "This is a technical discussion about Kubernetes and cloud-native architecture."
}

{
    "text": "The library is a quiet and peaceful place where people go to read, study, and learn. The shelves are filled with books on every subject imaginable."
}

High Temperature — Higher temperature for more varied transcription

const response = await env.AI.run(
  'openai/gpt-4o-transcribe',
  {
    file: 'https://cdn.openai.com/API/docs/audio/echo.wav',
    temperature: 0.5,
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Input / Output JSON

Input
Output

{
    "file": "https://cdn.openai.com/API/docs/audio/echo.wav",
    "temperature": 0.5
}

{
    "text": "In the heart of the city, there is a large park where people go to relax and enjoy nature. The park has a beautiful pond with ducks and swans."
}

file

stringrequiredThe audio file as a URL or data URI (data:audio/...;base64,...). Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm.

language

stringThe language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.

prompt

stringAn optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

temperature

numberrequireddefault: 0minimum: 0maximum: 1The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

text

stringThe transcribed text.

API Schemas

Input
Output

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "file": {
      "description": "The audio file as a URL or data URI (data:audio/...;base64,...). Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm.",
      "type": "string"
    },
    "language": {
      "description": "The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.",
      "type": "string"
    },
    "prompt": {
      "description": "An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.",
      "type": "string"
    },
    "temperature": {
      "description": "The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.",
      "default": 0,
      "type": "number",
      "minimum": 0,
      "maximum": 1
    }
  },
  "required": [
    "file",
    "temperature"
  ],
  "additionalProperties": false
}

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "text": {
      "description": "The transcribed text.",
      "type": "string"
    }
  },
  "required": [
    "text"
  ],
  "additionalProperties": false
}