Text-To-Speech Configuration

{ 
    "TTSType": "tencent", // String TTS type, currently supports "tencent" and "minixmax", support for other vendors is ongoing.
    "AppId": "Your Application ID", // String, required
    "SecretId": "Your Secret ID", // String, required
    "SecretKey": "Your Secret Key", // String, required
    "VoiceType": 101001, // Integer, required, voice ID, including standard timbre and premium timbre. The premium timbre has higher realism and a different price from the standard timbre. See the Text To Speech billing overview for details. For the complete list of voice IDs, see the Text To Speech timbre list.
    "Speed": 1.25, // Integer, optional, speech speed, range: [-2, 6], corresponding to different speech speeds: -2: represents 0.6 times, -1: represents 0.8 times, 0: represents 1.0 times (default), 1: represents 1.2 times, 2: represents 1.5 times, 6: represents 2.5 times. If you need a more detailed speech speed, you can retain 2 decimal places, such as 0.5/1.25/2.81, etc. For the conversion between parameter values and actual speech speed, see Speech Speed Conversion.
    "Volume": 5, // Integer, optional, volume level, range: [0, 10], corresponding to 11 levels of volume, default value is 0, representing normal volume.
    "PrimaryLanguage": 1, // Integer, optional primary language 1 - Chinese (default) 2 - English 3 - Japanese
    "FastVoiceType": "xxxx"   // optional parameter, parameter for Voice Reproduce 
}

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

{
    "TTSType": "azure", // required: String TTS type
    "SubscriptionKey": "xxxxxxxx", // required: String Subscription Key
    "Region": "chinanorth3",  // required: String Region of subscription
    "VoiceName": "zh-CN-XiaoxiaoNeural", // required: String Voice name is required
    "Language": "zh-CN", // required: String Language for synthesis  
    "Rate": 1 // optional: float speech speed 0.5–2 Default is 1
}

{
    "TTSType": "cartesia", // required: String TTS type 
    "Model": "sonic-multilingual", // required model
    "APIKey": "eyxxxx", // required: obtained API key
    "VoiceId": "eda5bbff-1ff1-4886-8ef1-4e69a77640a0" // required sound id https://play.cartesia.ai/
}

{
    "TTSType": "elevenlabs", // required: String TTS type 
    "Model": "eleven_turbo_v2_5", // required: model type
    "APIKey": "eyxxxx",
    "VoiceId": "eda5bbff-1ff1-4886-8ef1-4e69a77640a0" // Voice type https://elevenlabs.io/docs/api-reference/get-voices
}

{
  "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 output audio format, such as mp3, ogg_opus, pcm, wav, default is wav, currently only supports pcm and wav
  "SampleRate": 16000,  // Integer, optional, audio sample rate, default is 16000 (16kHz), recommended value is 16000
  "AudioChannel": 1,    // Integer, optional, audio channel quantity, value: 1 or 2, default is 1  
}