tencent cloud

{
    "TTSType": "tencent", // String TTS type, currently supports "tencent" and "minixmax", other vendors support in progress
    "AppId": "Your application ID", // String required
    "SecretId": "Your Secret ID", // String Required
    "SecretKey":  "Your Secret Key", // String Required
    "VoiceType": 101001, // Integer Required, Sound quality ID, includes standard and premium sound quality. Premium sound quality is more realistic and differently priced than standard sound quality. See TTS billing overview for details. For the full list of sound quality IDs, see the TTS sound quality list.
    "Speed": 1.25, // Integer Optional, speech speed, range: [-2,6], corresponding to different speeds: -2: represents 0.6x -1: represents 0.8x 0: represents 1.0x (default) 1: represents 1.2x 2: represents 1.5x 6: represents 2.5x For more precise speed control, you can retain two decimal places, such as 0.5/1.25/2.81, etc. For parameter value to actual speed conversion, refer to Speed Conversion
    "Volume": 5, // Integer Optional, Volume level, range: [0,10], corresponding to 11 levels of volume, default is 0, which represents normal volume.
    "PrimaryLanguage": 1, // Integer Optional, Primary language 1- Chinese (default) 2- English 3- Japanese
    "FastVoiceType": "xxxx"   // Optional parameter, Fast VRS parameter
  }

{
        "TTSType": "minimax",  // String TTS type,
        "Model": "speech-01-turbo",
        "APIUrl": "https://api.minimax.chat/v1/t2a_v2",
        "APIKey": "eyxxxx",
        "GroupId": "181000000000000",
        "VoiceType":"female-tianmei-yujie",
        "Speed": 1.2
}

{
    "TTSType": "volcengine",  // Required: String TTS type
    "AppId" : "xxxxxxxx",   // Required: String Volcano Engine assigned AppId
    "Token" : "TY9d4sQXHxxxxxxx", // Required: String type Volcano Engine access token
    "Speed" : 1.0,            // Optional parameter: Playback speed, default is 1.0
    "Volume": 1.0,            // Optional parameter: Volume, default is 1.0
    "Cluster" : "volcano_tts", // Optional parameter: Business cluster, default is volcano_tts
    "VoiceType" : "zh_male_aojiaobazong_moon_bigtts"   // Sound quality type, default is the sound quality of the large model TTS. If using normal TTS, fill in the corresponding sound quality type. Incorrect sound quality type will result in no sound.
}

{
    "TTSType": "azure", // Required: String TTS type
    "SubscriptionKey": "xxxxxxxx", // Required: String subscription key
    "Region": "chinanorth3",  // Required: String subscription region
    "VoiceName": "zh-CN-XiaoxiaoNeural", // Required: String Timbre Name required
    "Language": "zh-CN", // Required: String Language for synthesis
    "Rate": 1 // Optional: float Playback Speed 0.5-2 default is 1
}

{
  "TTSType": "custom", // Required String
  "APIKey": "ApiKey", // Required String for Authentication
  "APIUrl": "http://0.0.0.0:8080/stream-audio" // Required String, TTS API URL
  "AudioFormat": "wav", // String, optional, expected audio format, such as mp3, ogg_opus, pcm, wav, default is wav, currently only pcm and wav are supported,
  "SampleRate": 16000,  // Integer, optional, audio sample rate, default is 16000 (16k), recommended value is 16000
  "AudioChannel": 1,    // Integer, optional, number of audio channels, values: 1 or 2, default is 1
}