Overview and SDK Code Examples

Step 1: Install the SDK

Install the Alibaba Cloud SDK for Python.

pip install aliyun-python-sdk-core

Step 2: Clone and query voices

Use the following code to call the voice cloning API:

import os
import json
import time

from aliyunsdkcore.client import AcsClient
from aliyunsdkcore.request import CommonRequest

# Read the AccessKey ID and AccessKey secret from environment variables.
client = AcsClient(os.environ.get('ALIYUN_AK_ID'), os.environ.get('ALIYUN_AK_SECRET'))
domain = 'nls-slp.cn-shanghai.aliyuncs.com'
version = '2019-08-19'

def build_request(api_name, method):
    request = CommonRequest()
    request.set_domain(domain)
    request.set_version(version)
    request.set_action_name(api_name)
    request.set_method(method)
    request.set_protocol_type('https')
    return request

def cosy_clone(voice_prefix, url):
    clone_request = build_request('CosyVoiceClone', 'POST')
    clone_request.add_body_params('Url', url)
    clone_request.add_body_params('VoicePrefix', voice_prefix)
    # Set the read timeout to 15 seconds.
    clone_request.set_read_timeout(15)
    begin = int(round(time.time() * 1000))
    clone_response = client.do_action_with_exception(clone_request)
    end = int(round(time.time() * 1000))
    print(json.loads(clone_response))
    print('cost: {}'.format(end - begin))

def cosy_list(voice_prefix, page_index=1, page_size=10):
    list_request = build_request('ListCosyVoice', 'POST')
    list_request.add_body_params('VoicePrefix', voice_prefix)
    list_request.add_body_params('PageIndex', page_index)
    list_request.add_body_params('PageSize', page_size)
    list_response = client.do_action_with_exception(list_request)
    print(json.loads(list_response))

if __name__ == '__main__':
    # 1. Call CosyVoiceClone to clone a voice.
    audio_url = 'https://your-url'
    prefix = 'tongyi'  # Use letters or digits.
    cosy_clone(prefix, audio_url)
    # A successful call synchronously returns VoiceName in the format
    # cosyvoice-${voice_prefix}-${7 random characters}.

    # 2. Call ListCosyVoice to query voice statuses for the specified prefix.
    cosy_list(prefix)

For more information, see the CosyVoice voice cloning API.

Step 3: Use the cloned voice

When calling CosyVoice speech synthesis, set the voice field to the VoiceName returned by voice cloning. For details, see the CosyVoice speech synthesis API reference.

Step 1: Install the SDK

Add the following dependency to your Maven project. This example uses aliyun-java-sdk-core 4.6.4.

<dependency>
    <groupId>com.aliyun</groupId>
    <artifactId>aliyun-java-sdk-core</artifactId>
    <version>4.6.4</version>
</dependency>

Step 2: Clone and query voices

Use the following code to call the voice cloning API:

package org.example;

import com.aliyuncs.CommonRequest;
import com.aliyuncs.CommonResponse;
import com.aliyuncs.DefaultAcsClient;
import com.aliyuncs.IAcsClient;
import com.aliyuncs.exceptions.ClientException;
import com.aliyuncs.exceptions.ServerException;
import com.aliyuncs.http.MethodType;
import com.aliyuncs.http.ProtocolType;
import com.aliyuncs.profile.DefaultProfile;

public class CosyVoiceDemo {
    // Endpoint
    private static final String DOMAIN = "nls-slp.cn-shanghai.aliyuncs.com";
    // API version
    private static final String API_VERSION = "2019-08-19";

    private static final IAcsClient client;

    static {
        // Create and initialize the DefaultAcsClient instance.
        DefaultProfile profile = DefaultProfile.getProfile(
                "cn-shanghai",
                // Read the AccessKey ID and AccessKey secret from environment variables.
                System.getenv("ALIYUN_AK_ID"),
                System.getenv("ALIYUN_AK_SECRET"));
        client = new DefaultAcsClient(profile);
    }

    public static void main(String[] args) throws InterruptedException {
        String voicePrefix = "tongyi";
        String url = "your-file-url";
        cosyClone(voicePrefix, url);
        cosyList(voicePrefix);
    }

    private static void cosyList(String voicePrefix) {
        CommonRequest request = buildRequest("ListCosyVoice");
        request.putBodyParameter("VoicePrefix", voicePrefix);
        String response = sendRequest(request);
        System.out.println(response);
    }

    private static void cosyClone(String voicePrefix, String url) {
        CommonRequest cloneRequest = buildRequest("CosyVoiceClone");
        cloneRequest.putBodyParameter("VoicePrefix", voicePrefix);
        cloneRequest.putBodyParameter("Url", url);
        // Set the read timeout to 15 seconds.
        cloneRequest.setSysReadTimeout(15000);
        long startTime = System.currentTimeMillis();
        String response = sendRequest(cloneRequest);
        long endTime = System.currentTimeMillis();
        System.out.println(response);
        System.out.println("cost: "+ (endTime - startTime) + " ms");
    }

    private static CommonRequest buildRequest(String popApiName) {
        CommonRequest request = new CommonRequest();
        request.setMethod(MethodType.POST);
        request.setDomain(DOMAIN);
        request.setVersion(API_VERSION);
        request.setAction(popApiName);
        request.setProtocol(ProtocolType.HTTPS);
        return request;
    }

    private static String sendRequest(CommonRequest request) {
        try {
            CommonResponse response = client.getCommonResponse(request);
            return response.getData();
        } catch (ServerException e) {
            e.printStackTrace();
        } catch (ClientException e) {
            e.printStackTrace();
        }
        return null;
    }
}

For more information, see the CosyVoice voice cloning API.

Step 3: Use the cloned voice

When calling CosyVoice speech synthesis, set the voice field to the VoiceName returned by voice cloning. For details, see the CosyVoice speech synthesis API reference.