怎样添加自己的Azure API？/ Add custom API function

[anh3lang]

Firstly, i would like to say that you have made a great app, at least for me!
Your app have worked very well, but sometimes I run into the situation that said "bad handshake" error. We know that the reasons behind the limit of Azure Demo API, and it take time for the app to work normal again. And you have to updated new API in the meantime, right? So, the main point of this post is it is better to have the function in which the end user can use their own API. Thanks for your great app!

[jing332]

Since I can't meet the conditions for creating an Azure account, I can't support the official Azure API.

[jing332]

However, you can use custom TTS, copy to clipboard, and then import the sample (not guaranteed to be available)
复制到剪贴板并导入配置：

URL: https://pastebin.com/raw/f935zwtQ

{
    "group": {
        "id": 1674742541938,
        "name": "Custom",
        "order": 12
    },
    "list": [
        {
            "id": 1111111,
            "groupId": 1674742541938,
            "displayName": "Azure eastasia",
            "tts": {
                "#type": "http",
                "url": "https://eastasia.tts.speech.microsoft.com/cognitiveservices/v1,{\n    \"method\": \"POST\",\n    \"body\": \"<speak version=\\\"1.0\\\" xml:lang=\\\"zh-CN\\\"><voice name=\\\"zh-CN-XiaoxiaoNeural\\\"><prosody rate=\\\"{{speakSpeed}}%\\\" pitch=\\\"0%\\\">{{speakText}}</prosody></voice></speak>\"\n}",
                "header": "{\n  \"Ocp-Apim-Subscription-Key\": \"API-KEY\",\n  \"Content-Type\": \"application/ssml+xml\",\n  \"X-Microsoft-OutputFormat\": \"audio-16khz-128kbitrate-mono-mp3\",\n  \"User-Agent\": \"TTS Server\"\n}",
                "rate": 20,
                "audioFormat": {
                }
            }
        }
    ]
}

Then replace API-KEY with your key
然后替换 API-KEY 为你的Azure密钥

[anh3lang]

It is very helpful! Thanks!

[dullwolfs]

可以添加我自己封装的API吗？我接口返回是base64的音频字符串

[jing332]

插件TTS可以做到

[jing332]

有示例请求和响应嘛？

[dullwolfs]

有示例请求和响应嘛？

没事了，我打算弄新API，响应给你音频流，你做的APP插件就可以识别到了，我弄了一个网址，服务器存上百上千个模型，有原神、碧蓝档案、柚子社、赛马娘、还有一些虚拟主播等。http://soundai.natapp1.cc/

[jing332]

ok, 具体请求你可以参考内置的azure插件

[jing332]

有示例请求和响应嘛？

没事了，我打算弄新API，响应给你音频流，你做的APP插件就可以识别到了，我弄了一个网址，服务器存上百上千个模型，有原神、碧蓝档案、柚子社、赛马娘、还有一些虚拟主播等。http://soundai.natapp1.cc/

https://jt12.de/SYV2_4/2023/05/03/8/37/01/16830742216451acad9dd2f.json
我抽空写了个VITS插件，确保为最新开发板， 通过网络链接导入。
就是这延迟实在太高，基本都要等个5s以上，没法听