如何使用Google TTS生成音频文件?

时间:2019-01-22 11:52:07

标签: text-to-speech speech

如何在C#上使用Google TextToSpeech API生成音频文件? 我想为此项目使用Google API,能否提供一些示例或想法?

1 个答案:

答案 0 :(得分:0)

使用Google TTS的第一步;在NuGet上将Google Cloud TextToSpeech添加到项目中。

第二步是https://cloud.google.com/的注册,因为在此链接的注册后google给出了一个json文件,您需要该json文件才能使用该API(json文件:“ XXXXXXXXXXXX.json”)。那是主要服务,您可以免费试用12个月。

enter image description here

       private void GenerateVoice(string text, string type)
    {
        var credentials = GoogleCredential.FromFile(Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.Desktop), "XXXXXXXXXXXX.json"));
        var client = TextToSpeechClient.Create(credentials);


        var response = client.SynthesizeSpeech
        (
            new SynthesisInput()  //Text field
            {
                Text = text
            },
            new VoiceSelectionParams()  //Language and Voice type field u can use normal or VaweNet sound types
            {
                LanguageCode = "tr-TR",
                Name = type
            },
            new AudioConfig() //File type field
            {
                AudioEncoding = AudioEncoding.Mp3
            }
        );
        var speechFile = Path.Combine(Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.Desktop), "Ka_Ya.mp3"));
        File.WriteAllBytes(speechFile, response.AudioContent);
    }

    protected void btnGenerate_Click(object sender, EventArgs e)
    {
        if (txtDesc.Text.Trim().Length > 0)
        {
            GenerateVoice(txtDesc.Text, cmbType.Text);
        }
    }

希望本文对您有所帮助。

最诚挚的问候