How to quickly call the Alibaba Cloud Model Studio speech model service-Intelligent Speech Interaction(ISI)-阿里云帮助中心

This topic describes how to quickly use the Alibaba Cloud Model Studio speech model service.

Prerequisites

You have activated the service and obtained an API key. For more information, see Obtain and configure an API key and Configure an API key as an environment variable.
You have installed the software development kit (SDK). For more information, see Install the SDK.

Sample code

The following example shows how to call the Paraformer speech recognition file transcription API to transcribe an audio file from a URL.

Note

Replace your-dashscope-api-key in the example with your API key to run the code.
The file specified by the URL cannot be larger than 2 GB.
The file_urls parameter supports multiple file URLs. This example demonstrates transcription for only a single file URL.

Python

# For prerequisites running the following sample, visit https://help.aliyun.com/document_detail/611472.html

import dashscope
from urllib import request
import json

dashscope.api_key='your-dashscope-api-key'

task_response=dashscope.audio.asr.Transcription.async_call(
    model='paraformer-v1',
    file_urls=['https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world.wav']
    )

transcription_response=dashscope.audio.asr.Transcription.wait(task=task_response.output.task_id)

transcription_url=transcription_response.output['results'][0]['transcription_url']
transcription_results=json.loads(request.urlopen(transcription_url).read().decode('utf8'))
print(json.dumps(transcription_results, indent=4, ensure_ascii=False))

A successful call returns a transcription result, as shown in the following example.

{
    "file_url": "https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world.wav",
    "properties": {
        "audio_format": "pcm_s16le",
        "channels": [
            0
        ],
        "original_sampling_rate": 16000,
        "original_duration": 4087
    },
    "transcripts": [
        {
            "channel_id": 0,
            "content_duration": 3840,
            "text": "Hello, world, from the Alibaba DAMO Academy Speech Lab.",
            "sentences": [
                {
                    "begin_time": 0,
                    "end_time": 3840,
                    "text": "Hello, world, from the Alibaba DAMO Academy Speech Lab.",
                    "words": [
                        {
                            "begin_time": 0,
                            "end_time": 540,
                            "text": "Hello",
                            "punctuation": ", "
                        },
                        {
                            "begin_time": 540,
                            "end_time": 1260,
                            "text": "world",
                            "punctuation": ", "
                        },
                        {
                            "begin_time": 1260,
                            "end_time": 1600,
                            "text": "from",
                            "punctuation": " "
                        },
                        {
                            "begin_time": 1600,
                            "end_time": 1800,
                            "text": "the",
                            "punctuation": " "
                        },
                        {
                            "begin_time": 1800,
                            "end_time": 2300,
                            "text": "Alibaba",
                            "punctuation": " "
                        },
                        {
                            "begin_time": 2300,
                            "end_time": 2700,
                            "text": "DAMO",
                            "punctuation": " "
                        },
                        {
                            "begin_time": 2700,
                            "end_time": 3200,
                            "text": "Academy",
                            "punctuation": " "
                        },
                        {
                            "begin_time": 3200,
                            "end_time": 3600,
                            "text": "Speech",
                            "punctuation": " "
                        },
                        {
                            "begin_time": 3600,
                            "end_time": 3840,
                            "text": "Lab",
                            "punctuation": "."
                        }
                    ]
                }
            ]
        }
    ]
}

Learn more

For more information about how to call the Paraformer speech recognition API, see API details.