语音合成API

接口描述

语音合成接口。

请求说明

URL

https://openapi.sys303.com/api/cognitive/tts/stream

参数

Header参数

参数	值
Content-Type	application/json
X-Secret	点击获取

Body参数

参数	是否必选	类型	可选值范围	说明
lang	是	int	[0, 1, 4, 5]	0：藏文-卫藏，1：中文，4：藏文-康巴，5：藏文-安多
vcn	否	string	["xiaoxiao","yunjian"]	【当lang为1时可选，可选"xiaoxiao"和"yunjian"；lang为其余值，传入空。】
inputText	是	string		待语音合成文字【unicode 长度3000字以内】

请求样例

bash

curl https://openapi.sys303.com/api/cognitive/tts/stream \
  --request POST \
  --header 'Accept: */*' \
  --header 'Content-Type: application/json' \
  --header 'X-Secret: {X-Secret}' \
  --data '{
  "lang": 0,
  "inputText": "语音合成文字",
  "vcn": ""
}' \
  --output out.pcm

python

import requests

url = "https://openapi.sys303.com/api/cognitive/tts/stream"

headers = {
    "Accept": "*/*",
    "Content-Type": "application/json",
    "X-Secret": "{your X-Secret}"
}

data = {
    "lang": 0,
    "inputText": "语音合成文字",
    "vcn": ""
}

resp = requests.post(url, headers=headers, json=data, stream=True)

if resp.status_code == 200:
    with open("out.pcm", "wb") as f:
        for chunk in resp.iter_content(chunk_size=4096):
            if chunk:
                f.write(chunk)
    print("保存成功 out.pcm")
else:
    print("请求失败")
    print(resp.text)

C#

using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;
using System.IO;

class Program
{
    static async Task Main()
    {
        var url = "https://openapi.sys303.com/api/cognitive/tts/stream";

        using var client = new HttpClient();

        client.DefaultRequestHeaders.Add("Accept", "*/*");
        client.DefaultRequestHeaders.Add("X-Secret", "{your X-Secret}");

        var json = @"{
            ""lang"": 0,
            ""inputText"": ""语音合成文字"",
            ""vcn"": """"
        }";

        var content = new StringContent(json, Encoding.UTF8, "application/json");

        var response = await client.PostAsync(url, content);

        if (response.IsSuccessStatusCode)
        {
            var bytes = await response.Content.ReadAsByteArrayAsync();
            await File.WriteAllBytesAsync("out.pcm", bytes);
            Console.WriteLine("保存成功 out.pcm");
        }
        else
        {
            var err = await response.Content.ReadAsStringAsync();
            Console.WriteLine("请求失败: " + err);
        }
    }
}

Java

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.nio.file.Path;

public class TtsDemo {
    public static void main(String[] args) throws Exception {

        String json = """
        {
          "lang": 0,
          "inputText": "语音合成文字",
          "vcn": ""
        }
        """;

        HttpClient client = HttpClient.newHttpClient();

        HttpRequest request = HttpRequest.newBuilder()
                .uri(URI.create("https://openapi.sys303.com/api/cognitive/tts/stream"))
                .header("Accept", "*/*")
                .header("Content-Type", "application/json")
                .header("X-Secret", "{your X-Secret}")
                .POST(HttpRequest.BodyPublishers.ofString(json))
                .build();

        HttpResponse<Path> response = client.send(
                request,
                HttpResponse.BodyHandlers.ofFile(Path.of("out.pcm"))
        );

        System.out.println("HTTP状态码: " + response.statusCode());
        System.out.println("已保存 out.pcm");
    }
}

返回说明

正常请求

返回PCM文件流。16000 码率；单声道。 可以使用 ffplay -f s16le -ar 16000 out.pcm 进行播放验证。

异常请求参数说明

字段	是否必选	类型	状态	说明
traceId	是	String	-	唯一的traceId，用于问题定位
msgId	是	String	-	业务状态码
msg	是	String		错误描述
data	是	String	-	空值

返回样例

失败

认证失败：

{
  "traceId": "0HNLN3J9DCJSE:00000001",
  "msgId": "4011001",
  "msg": "AuthFailed",
  "data": null
}

传入参数错误：

{
    "traceId": "0HNL06O44AU14:00000001",
    "msgId": "500",
    "msg": "Specified argument was out of the range of valid values. (Parameter 'lang')",
    "data": null
}

次数不足：

{
    "traceId": "0HNL06O44AU1F:00000001",
    "msgId": "2001001",
    "msg": "InsufficientInventory",
    "data": null
}

字符长度超长：

{
  "traceId": "0HNL06O44AUVB:00000001",
  "msgId": "4004002",
  "msg": "InputTooLong",
  "data": null
}