Reconhecimento de fala não em tempo real (Qwen-Audio-3.0-ASR-Flash/Fun-ASR-Flash) HTTP API

curl --location --request POST 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
     --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
     --header "Content-Type: application/json" \
     --header "X-DashScope-SSE: enable" \
     --data '{
    "model": "qwen-audio-3.0-asr-flash",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": "{YOUR_AUDIO_URL}"
                        }
                    }
                ]
            }
        ]
    },
    "parameters": {
        "format": "wav",
        "sample_rate": "16000"
    }
}'

curl --location --request POST 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
     --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
     --header "Content-Type: application/json" \
     --header "X-DashScope-SSE: disable" \
     --data '{
    "model": "qwen-audio-3.0-asr-flash",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_text",
                        "text": "Hello"
                    }
                ]
            },
            {
                "role": "assistant",
                "content": [
                    {
                        "type": "text",
                        "text": "Hello, I'm Qwen. How can I help you?"
                    }
                ]
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": "{YOUR_AUDIO_URL}"
                        }
                    }
                ]
            }
        ]
    },
    "parameters": {
        "format": "wav",
        "sample_rate": "16000"
    }
}'

curl --location --request POST 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
     --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
     --header "Content-Type: application/json" \
     --header "X-DashScope-SSE: enable" \
     --data '{
    "model": "qwen-audio-3.0-asr-flash",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_text",
                        "text": "Hello"
                    }
                ]
            },
            {
                "role": "assistant",
                "content": [
                    {
                        "type": "text",
                        "text": "Hello, I'm Qwen. How can I help you?"
                    }
                ]
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": "{YOUR_AUDIO_URL}"
                        }
                    }
                ]
            }
        ]
    },
    "parameters": {
        "format": "wav",
        "sample_rate": "16000"
    }
}'

import base64, pathlib
import os
import requests

# Replace with the path to your own audio file and make sure it meets the audio requirements
file_path = pathlib.Path("{YOUR_AUDIO_FILE}")
base64_str = base64.b64encode(file_path.read_bytes()).decode()
data_uri = f"data:audio/wav;base64,{base64_str}"

# Replace "{WorkspaceId}" with your actual workspace ID
url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation"

headers = {
    "Authorization": f"Bearer {os.environ['DASHSCOPE_API_KEY']}",
    "Content-Type": "application/json",
    "X-DashScope-SSE": "disable",
}

payload = {
    "model": "qwen-audio-3.0-asr-flash",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": data_uri,
                        },
                    }
                ],
            }
        ]
    },
    "parameters": {
        "format": "wav",
        "sample_rate": "16000",
    },
}

response = requests.post(url, headers=headers, json=payload)
print(response.status_code)
print(response.json())

curl --location --request POST 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
     --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
     --header "Content-Type: application/json" \
     --header "X-DashScope-SSE: disable" \
     --data '{
    "model": "qwen-audio-3.0-asr-flash",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": "{YOUR_AUDIO_URL}"
                        }
                    }
                ]
            }
        ]
    },
    "parameters": {
        "format": "wav",
        "sample_rate": "16000",
        "vocabulary": {"John Smith": 5, "Jane Doe": 5}
    }
}'