Alibaba Cloud Model Studio:Qwen-Omni

import os
from openai import OpenAI

client = OpenAI(
    # API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following is the URL for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3-omni-flash",
    messages=[{"role": "user", "content": "Who are you"}],

    # Enable or disable thinking mode. Audio output is not supported in thinking mode. qwen-omni-turbo does not support setting enable_thinking.
    extra_body={'enable_thinking': True},

    # Set the output data modality. Two are currently supported in non-thinking mode: ["text","audio"] and ["text"]. Only ["text"] is supported in thinking mode.
    modalities=["text"],

    # Set the voice. The audio parameter is not supported in thinking mode.
    # audio={"voice": "Cherry", "format": "wav"},
    # stream must be set to True to avoid errors.
    stream=True,
    stream_options={"include_usage": True},
)

for chunk in completion:
    if chunk.choices:
        print(chunk.choices[0].delta)
    else:
        print(chunk.usage)

import OpenAI from "openai";

const openai = new OpenAI(
    {
        // API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
        apiKey: process.env.DASHSCOPE_API_KEY,
        // The following is the URL for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1
        baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
    }
);
const completion = await openai.chat.completions.create({
    model: "qwen3-omni-flash",
    messages: [
        { role: "user", content: "Who are you?" }
    ],

    // stream must be set to True to avoid errors.
    stream: true,
    stream_options: {
        include_usage: true
    },
    // Enable or disable thinking mode. Audio output is not supported in thinking mode. qwen-omni-turbo does not support setting enable_thinking.
    extra_body:{'enable_thinking': true},
    //  Set the output data modality. Two are currently supported in non-thinking mode: ["text","audio"] and ["text"]. Only ["text"] is supported in thinking mode.
    modalities: ["text"],
    // Set the voice. The audio parameter is not supported in thinking mode.
    //audio: { voice: "Cherry", format: "wav" }
});

for await (const chunk of completion) {
    if (Array.isArray(chunk.choices) && chunk.choices.length > 0) {
        console.log(chunk.choices[0].delta);
    } else {
        console.log(chunk.usage);
    }
}

# ======= Important Note =======
# API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# The following is the URL for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
# === Delete this comment before execution ===

curl -X POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3-omni-flash",
    "messages": [
        {
            "role": "user",
            "content": "Who are you?"
        }
    ],
    "stream":true,
    "stream_options":{
        "include_usage":true
    },
    "modalities":["text"],
    "enable_thinking": true
}'

import os
from openai import OpenAI

client = OpenAI(
    # API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following is the URL for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3-omni-flash", # When the model is Qwen3-Omni-Flash, run in non-thinking mode.
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
                    },
                },
                {"type": "text", "text": "What scene is depicted in the image?"},
            ],
        },
    ],
    # Set the output data modality. Two are currently supported: ["text","audio"] and ["text"].
    modalities=["text", "audio"],
    audio={"voice": "Cherry", "format": "wav"},
    # stream must be set to True to avoid errors.
    stream=True,
    stream_options={
        "include_usage": True
    }
)

for chunk in completion:
    if chunk.choices:
        print(chunk.choices[0].delta)
    else:
        print(chunk.usage)

import OpenAI from "openai";

const openai = new OpenAI(
    {
        // API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
        apiKey: process.env.DASHSCOPE_API_KEY,
        // The following is the URL for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1
        baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
    }
);
const completion = await openai.chat.completions.create({
    model: "qwen3-omni-flash", // When the model is Qwen3-Omni-Flash, run in non-thinking mode.
    messages: [
        {
            "role": "user",
            "content": [{
                "type": "image_url",
                "image_url": { "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg" },
            },
            { "type": "text", "text": "What scene is depicted in the image?" }]
        }],
    stream: true,
    stream_options: {
        include_usage: true
    },
    modalities: ["text", "audio"],
    audio: { voice: "Cherry", format: "wav" }
});

for await (const chunk of completion) {
    if (Array.isArray(chunk.choices) && chunk.choices.length > 0) {
        console.log(chunk.choices[0].delta);
    } else {
        console.log(chunk.usage);
    }
}

# ======= Important Note =======
# API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# The following is the URL for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
# === Delete this comment before execution ===


curl -X POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3-omni-flash",
    "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
          }
        },
        {
          "type": "text",
          "text": "What scene is depicted in the image?"
        }
      ]
    }
  ],
    "stream":true,
    "stream_options":{
        "include_usage":true
    },
    "modalities":["text","audio"],
    "audio":{"voice":"Cherry","format":"wav"}
}'

import os
from openai import OpenAI

client = OpenAI(
    # API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following is the URL for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3-omni-flash",# When the model is Qwen3-Omni-Flash, run in non-thinking mode.
    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",
                    },
                },
                {"type": "text", "text": "What is this audio about"},
            ],
        },
    ],
    # Set the output data modality. Two are currently supported: ["text","audio"] and ["text"].
    modalities=["text", "audio"],
    audio={"voice": "Cherry", "format": "wav"},
    # stream must be set to True to avoid errors.
    stream=True,
    stream_options={"include_usage": True},
)

for chunk in completion:
    if chunk.choices:
        print(chunk.choices[0].delta)
    else:
        print(chunk.usage)

import OpenAI from "openai";

const openai = new OpenAI(
    {
        // API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
        apiKey: process.env.DASHSCOPE_API_KEY,
        // The following is the URL for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1
        baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
    }
);
const completion = await openai.chat.completions.create({
    model: "qwen3-omni-flash", // When the model is Qwen3-Omni-Flash, run in non-thinking mode.
    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" },
            },
            { "type": "text", "text": "What is this audio about" }]
        }],
    stream: true,
    stream_options: {
        include_usage: true
    },
    modalities: ["text", "audio"],
    audio: { voice: "Cherry", format: "wav" }
});

for await (const chunk of completion) {
    if (Array.isArray(chunk.choices) && chunk.choices.length > 0) {
        console.log(chunk.choices[0].delta);
    } else {
        console.log(chunk.usage);
    }
}

# ======= Important Note =======
# API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# The following is the URL for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
# === Delete this comment before execution ===

curl -X POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3-omni-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"
          }
        },
        {
          "type": "text",
          "text": "What is this audio about"
        }
      ]
    }
  ],
    "stream":true,
    "stream_options":{
        "include_usage":true
    },
    "modalities":["text","audio"],
    "audio":{"voice":"Cherry","format":"wav"}
}'

import os
from openai import OpenAI

client = OpenAI(
    # API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following is the URL for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3-omni-flash", # When the model is Qwen3-Omni-Flash, run in non-thinking mode.
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "input_audio",
                    "input_audio": {
                        "data": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3",
                        "format": "mp3",
                    },
                },
                {"type": "text", "text": "What is this audio about"},
            ],
        },
        {
            "role": "assistant",
            "content": [{"type": "text", "text": "This audio says: Welcome to Alibaba Cloud"}],
        },
        {
            "role": "user",
            "content": [{"type": "text", "text": "Can you tell me about this company?"}],
        },
    ],
    # Set the output data modality. Two are currently supported: ["text","audio"] and ["text"].
    modalities=["text"],
    # stream must be set to True to avoid errors.
    stream=True,
    stream_options={"include_usage": True},
)

for chunk in completion:
    if chunk.choices:
        print(chunk.choices[0].delta)
    else:
        print(chunk.usage)

import OpenAI from "openai";

const openai = new OpenAI(
    {
        // API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
        apiKey: process.env.DASHSCOPE_API_KEY,
        // The following is the URL for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1
        baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
    }
);
const completion = await openai.chat.completions.create({
    model: "qwen3-omni-flash", // When the model is Qwen3-Omni-Flash, run in non-thinking mode.
    messages: [
        {
            "role": "user",
            "content": [
                {
                    "type": "input_audio",
                    "input_audio": {
                        "data": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3",
                        "format": "mp3",
                    },
                },
                { "type": "text", "text": "What is this audio about" },
            ],
        },
        {
            "role": "assistant",
            "content": [{ "type": "text", "text": "This audio says: Welcome to Alibaba Cloud" }],
        },
        {
            "role": "user",
            "content": [{ "type": "text", "text": "Can you tell me about this company?" }]
        }],
    stream: true,
    stream_options: {
        include_usage: true
    },
    modalities: ["text"]
});


for await (const chunk of completion) {
    if (Array.isArray(chunk.choices) && chunk.choices.length > 0) {
        console.log(chunk.choices[0].delta);
    } else {
        console.log(chunk.usage);
    }
}

# ======= Important Note =======
# API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# The following is the URL for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
# === Delete this comment before execution ===

curl -X POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "qwen3-omni-flash",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_audio",
          "input_audio": {
            "data": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
          }
        },
        {
          "type": "text",
          "text": "What is this audio about"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "type": "text",
          "text": "This audio says: Welcome to Alibaba Cloud"
        }
      ]
    },
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Can you tell me about this company?"
        }
      ]
    }
  ],
  "stream": true,
  "stream_options": {
    "include_usage": true
  },
  "modalities": ["text"]
}'