Alibaba Cloud Model Studio:Terjemahan audio dan video - Referensi API Qwen

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Berikut ini adalah URL wilayah Singapura. Ganti {WorkspaceId} dengan ID ruang kerja aktual Anda. URL berbeda-beda tergantung wilayah.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3-livetranslate-flash",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "input_audio",
                    "input_audio": {
                        "data": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250211/tixcef/cherry.wav",
                        "format": "wav",
                    },
                }
            ],
        }
    ],
    modalities=["text", "audio"],
    audio={"voice": "Cherry", "format": "wav"},
    stream=True,
    stream_options={"include_usage": True},
    extra_body={"translation_options": {"source_lang": "zh", "target_lang": "en"}},
)

for chunk in completion:
    print(chunk)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY,
    // Berikut ini adalah URL wilayah Singapura. Ganti {WorkspaceId} dengan ID ruang kerja aktual Anda. URL berbeda-beda tergantung wilayah.
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
});

async function main() {
    const completion = await client.chat.completions.create({
        model: "qwen3-livetranslate-flash",
        messages: [
            {
                role: "user",
                content: [
                    {
                        type: "input_audio",
                        input_audio: {
                            data: "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250211/tixcef/cherry.wav",
                            format: "wav",
                        },
                    },
                ],
            },
        ],
        modalities: ["text", "audio"],
        audio: { voice: "Cherry", format: "wav" },
        stream: true,
        stream_options: { include_usage: true },
        translation_options: { source_lang: "zh", target_lang: "en" },
    });

    for await (const chunk of completion) {
        console.log(JSON.stringify(chunk));
    }
}

main();

curl

## Berikut ini adalah URL wilayah Singapura. Ganti {WorkspaceId} dengan ID ruang kerja aktual Anda. URL berbeda-beda tergantung wilayah.
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions \
  -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-livetranslate-flash",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_audio",
            "input_audio": {
              "data": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250211/tixcef/cherry.wav",
              "format": "wav"
            }
          }
        ]
      }
    ],
    "modalities": ["text", "audio"],
    "audio": {
      "voice": "Cherry",
      "format": "wav"
    },
    "stream": true,
    "stream_options": {
      "include_usage": true
    },
    "translation_options": {
      "source_lang": "zh",
      "target_lang": "en"
    }
  }'

Input video

Untuk menerjemahkan video alih-alih audio, atur tipe konten menjadi video_url:

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "video_url",
                "video_url": {
                    "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241115/cqqkru/1.mp4"
                },
            }
        ],
    },
]

Semua parameter lain tetap sama.

Parameter wajib

Parameter opsional

Parameter pengambilan sampel

Untuk akurasi terjemahan, pertahankan parameter-parameter ini pada nilai default-nya.

Objek pesan

Array messages harus berisi tepat satu objek dengan role diatur ke user.

Properti item array content:

Objek input_audio:

Objek video_url:

Opsi terjemahan

Catatan: translation_options adalah parameter non-standar OpenAI. Di SDK Python, masukkan dalam extra_body. Di Node.js atau HTTP, masukkan di tingkat atas badan permintaan.

extra_body={"translation_options": {"source_lang": "zh", "target_lang": "en"}}

Opsi keluaran audio

Wajib saat modalities diatur ke ["text", "audio"].

Opsi streaming

Chunk teks

Berisi teks terjemahan bertahap dalam choices[0].delta.content:

{
  "id": "chatcmpl-c22a54b8-40cc-4a1d-988b-f84cdf86868f",
  "choices": [
    {
      "delta": {
        "content": null,
        "role": null,
        "audio": {
          "data": "///+//7////+////////////AAAAAAAAAAABA......",
          "expires_at": 1764755440,
          "id": "audio_c22a54b8-40cc-4a1d-988b-f84cdf86868f"
        }
      },
      "finish_reason": null,
      "index": 0
    }
  ],
  "created": 1764755440,
  "model": "qwen3-livetranslate-flash",
  "object": "chat.completion.chunk"
}

Chunk audio

Berisi segmen audio bertahap yang dikodekan Base64 dalam choices[0].delta.audio.data:

{
  "id": "chatcmpl-c22a54b8-40cc-4a1d-988b-f84cdf86868f",
  "choices": [
    {
      "delta": {
        "content": null,
        "role": null,
        "audio": {
          "data": "///+//7////+////////////AAAAAAAAAAABA......",
          "expires_at": 1764755440,
          "id": "audio_c22a54b8-40cc-4a1d-988b-f84cdf86868f"
        }
      },
      "finish_reason": null,
      "index": 0
    }
  ],
  "created": 1764755440,
  "model": "qwen3-livetranslate-flash",
  "object": "chat.completion.chunk"
}

Chunk penggunaan token

Dikembalikan sebagai chunk terakhir saat include_usage diatur ke true. Array choices kosong, dan usage berisi rincian penggunaan token:

{
  "id": "chatcmpl-c22a54b8-40cc-4a1d-988b-f84cdf86868f",
  "choices": [],
  "created": 1764755440,
  "model": "qwen3-livetranslate-flash",
  "object": "chat.completion.chunk",
  "usage": {
    "completion_tokens": 242,
    "prompt_tokens": 415,
    "total_tokens": 657,
    "completion_tokens_details": {
      "accepted_prediction_tokens": null,
      "audio_tokens": 191,
      "reasoning_tokens": null,
      "rejected_prediction_tokens": null,
      "text_tokens": 51
    },
    "prompt_tokens_details": {
      "audio_tokens": 415,
      "cached_tokens": null,
      "text_tokens": 0,
      "video_tokens": null
    }
  }
}

Catatan: Untuk input video, prompt_tokens_details.audio_tokens mencakup token audio yang diekstraksi dari video. video_tokens melaporkan jumlah token khusus video.

Bidang tanggapan

Bidang yang selalu bernilai null

Bidang-bidang berikut ada dalam tanggapan demi kompatibilitas OpenAI tetapi selalu mengembalikan null:

reasoning_content, function_call, refusal, tool_calls, logprobs, service_tier, system_fingerprint