gpt-4o-mini-audio-preview

This documentation is valid for the following list of our models:

• gpt-4o-mini-audio-preview

Model Overview

A preview release of the smaller GPT-4o Audio mini model. Handles both audio and text as input and output via the REST API. You can choose from a wide range of audio formats for output and specify the voice the model will use for audio responses.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

API Schema

Generate a conversational response using a language model.

post

Creates a chat completion using a language model, allowing interactive conversation by predicting the next response based on the given chat history. This is useful for AI-driven dialogue systems and virtual assistants.

Authorizations

Body

modelundefined · enumrequiredAvailable options:

frequency_penaltynumber | nullableoptional

logit_biasobject | nullableoptional

logprobsboolean | nullableoptional

top_logprobsnumber | nullableoptional

max_tokensnumber · min: 1optionalDefault: 512

max_completion_tokensinteger · min: 1optional

ninteger | nullableoptional

predictionobjectoptional

presence_penaltynumber | nullableoptional

seedinteger · min: 1optional

messagesone of[]required

streambooleanoptionalDefault: false

stream_optionsobjectoptional

top_pnumber · min: 0.1 · max: 1optional

temperaturenumber · max: 2optional

stopany ofoptional

toolsobject[]optional

tool_choiceany ofoptional

parallel_tool_callsbooleanoptional

reasoning_effortstring · enumoptionalAvailable options:

response_formatone ofoptional

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so

audioobject | nullableoptional

Parameters for audio output. Required when audio output is requested with modalities: ["audio"]

modalitiesstring · enum[] | nullableoptional

Output types that you would like the model to generate

web_search_optionsobjectoptional

This tool searches the web for relevant results to use in a response

Responses

post

HTTPcURLJavaScriptPython

POST /v1/chat/completions HTTP/1.1
Host: api.aimlapi.com
Authorization: Bearer <YOUR_AIMLAPI_KEY>
Content-Type: application/json
Accept: */*
Content-Length: 888

{
  "model": "gpt-4o-mini-audio-preview",
  "frequency_penalty": 1,
  "logit_bias": {
    "ANY_ADDITIONAL_PROPERTY": 1
  },
  "logprobs": true,
  "top_logprobs": 1,
  "max_tokens": 1,
  "max_completion_tokens": 1,
  "n": 1,
  "prediction": {
    "type": "content",
    "content": "text"
  },
  "presence_penalty": 1,
  "seed": 1,
  "messages": [
    {
      "role": "system",
      "content": "text",
      "name": "text"
    }
  ],
  "stream": true,
  "stream_options": {
    "include_usage": true
  },
  "top_p": 1,
  "temperature": 1,
  "stop": "text",
  "tools": [
    {
      "type": "function",
      "function": {
        "description": "text",
        "name": "text",
        "parameters": null,
        "strict": true,
        "required": [
          "text"
        ]
      }
    }
  ],
  "tool_choice": "none",
  "parallel_tool_calls": true,
  "reasoning_effort": "low",
  "response_format": {
    "type": "text"
  },
  "audio": {
    "format": "wav",
    "voice": "alloy"
  },
  "modalities": [
    "text"
  ],
  "web_search_options": {
    "search_context_size": "low",
    "user_location": {
      "approximate": {
        "city": "text",
        "country": "text",
        "region": "text",
        "timezone": "text"
      },
      "type": "approximate"
    }
  }
}

201Success

No Content