语音回复(chat)

请求参数

Header 参数

Body 参数application/json

示例

{
  "model": "gpt-4o-audio-preview",
  "modalities": [
    "audio",
    "text"
  ],
  "audio": {
    "format": "wav",
    "voice": "alloy"
  },
  "messages": [
    {
      "role": "user",
      "content": "请用中文回答：你能听到我的声音吗？并用语音回复我。"
    }
  ]
}

请求示例代码

Shell

JavaScript

Java

Swift

Go

PHP

Python

HTTP

C

C#

Objective-C

Ruby

OCaml

Dart

R

curl --location --request POST 'https://api.wenwen-ai.com/v1/chat/completions' \
--header 'Authorization: Bearer {API_KEY}' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "gpt-4o-audio-preview",
  "modalities": [
    "audio",
    "text"
  ],
  "audio": {
    "format": "wav",
    "voice": "alloy"
  },
  "messages": [
    {
      "role": "user",
      "content": "请用中文回答：你能听到我的声音吗？并用语音回复我。"
    }
  ]
}'

返回响应

🟢200成功

application/json

Body

示例

{
    "id": "chatcmpl-BqebNpDZkLbdiwDBINEDTuUBCQK5L",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "logprobs": null,
            "message": {
                "content": null,
                "refusal": null,
                "role": "assistant",
                "annotations": [],
                "audio": {
                    "id": "audio_686bb3bec2608191b1d7efbfbd8bdb51",
                    "data": "UklGRv////9XQVZFZ......AB4AgABcAFQAAwA=",
                    "expires_at": 1751892430,
                    "transcript": "是的，我可以听到你的声音。"
                },
                "function_call": null,
                "tool_calls": null
            }
        }
    ],
    "created": 1751888829,
    "model": "gpt-4o-audio-preview-2024-12-17",
    "object": "chat.completion",
    "service_tier": "default",
    "system_fingerprint": "fp_bf8dbd2ceb",
    "usage": {
        "completion_tokens": 67,
        "prompt_tokens": 27,
        "total_tokens": 94,
        "completion_tokens_details": {
            "accepted_prediction_tokens": 0,
            "audio_tokens": 50,
            "reasoning_tokens": 0,
            "rejected_prediction_tokens": 0,
            "text_tokens": 17
        },
        "prompt_tokens_details": {
            "audio_tokens": 0,
            "cached_tokens": 0,
            "text_tokens": 27,
            "image_tokens": 0
        }
    }
}