텍스트 음성 변환 구성

{
  "TTSType": "flow",  // [Required] Fixed value.
  "VoiceId": "v-female-R2s4N9qJ", // [Required] Premium or Cloned Voice ID. Refer to the "Voice List" below for available IDs
  "Model": "flow_01_turbo", //[Required] The current default TTS model version.
  "Speed": 1.0,    //[Optional] Speech rate. Range: [0.5-2.0]. Default: 1.0. Higher values indicate faster speech.
  "Volume": 1.0,   // [Optional] Volume level. Range: [0, 10]. Default: 1.0. Higher values indicate louder volume.
  "Pitch": 0,   // [Optional] Pitch adjustment. Range: [-12, 12]. Default: 0 (original tone).Higher values result in a higher pitch.
  "Language": "zh" // [Optional] Recommended. Language ID; Supports "zh" (Chinese), "en" (English), "yue" (Chinese-Cantonese). Standard: ISO 639-1.
}

{
    "TTSType": "azure", // Required. TTS type in string format.
    "SubscriptionKey": "xxxxxxxx", // Required. Subscription key in string format.
    "Region": "southeastasia",  // Required. Subscription region in string format.
    "VoiceName": "en-US-AmandaMultilingualNeural", // Required. Timbre name in string format.
    "Language": "en-US", // Required. Language for TTS in string format. 
    "Rate": 1 // Optional. Speech speed in float format. Value range: 0.5–2. Default value: 1.
}

{
    "TTSType": "cartesia", // Required. TTS type in string format. 
    "Model": "sonic-multilingual", // Required. Model.
    "APIKey": "eyxxxx", // Required. Obtained API key.
    "VoiceId": "eda5bbff-1ff1-4886-8ef1-4e69a77640a0" // Required. Timbre ID. Visit https://play.cartesia.ai/ for details.
}

{
    "TTSType": "elevenlabs", // // Required. String. Specifies the TTS provider type.
    "Model": "eleven_turbo_v2_5", // Required. Model Type.
    "APIKey": "eyxxxx", // Required. The API key used to authenticate requests.
    "VoiceId": "eda5bbff-1ff1-4886-8ef1-4e69a77640a0" // Required. The voice ID. See https://elevenlabs.io/docs/api-reference/get-voices for details.
}

{ 
    "TTSType": "tencent", // TTS type in string format. Valid values: "tencent" and "minixmax". Other vendors will be supported in future versions.
    "AppId": "Your application ID", // Required. The value is in string format.
    "SecretId": "Your key ID", // Required. The value is in string format.
    "SecretKey": "Your key", // Required. The value is in string format.
    "VoiceType": 101001, // Required. Timbre ID in integer format. Standard timbre and premium timbre are supported. The premium timbre is more real, and its price differs from that of the standard timbre. See the TTS billing overview for details. For the complete list of timbre IDs, see the TTS timbre list.
    "Speed": 1.25, // Optional. Speech speed in integer format. Value range: [-2, 6], corresponding to different speech speeds. -2: 0.6 times; -1: 0.8 times; 0: 1.0 times (default value); 1: 1.2 times; 2: 1.5 times; 6: 2.5 times. If you need a more fine-grained speech speed, the value can be accurate to 2 decimal places, such as 0.5, 1.25, and 2.81. For the conversion between the parameter value and actual speech speed, see Speech Speed Conversion.
    "Volume": 5, // Optional. Volume level in integer format. Value range: [0, 10], corresponding to 11 volume levels. The default value is 0, representing the normal volume.
    "PrimaryLanguage": 1, // Optional. Primary language in integer format. 1: Chinese (default value); 2: English; 3: Japanese.
    "FastVoiceType": "xxxx"   // Optional. Parameter for fast voice cloning.
}

{
  "TTSType": "minimax", // Required. String. Specifies the TTS provider type.
  "Model": "speech-02-turbo", // Required. The TTS model type.
  "APIUrl": "https://api.minimax.chat/v1/t2a_v2",// Required. The API endpoint URL.
  "APIKey": "eyxxxx",// Required. String. The API key used for authentication.
  "GroupId": "181000000000000", // Required. The MiniMax group ID associated with your account.
  "VoiceType": "female-tianmei", // Required. String. The requested voice identifier (voice_id).
  "Speed": 1.2 // Optional. Float. Speech speed multiplier. Valid range: [0.5, 2.0]. Default is 1.0.
}

{
  "TTSType": "custom", // Required. The value is in string format.
  "APIKey": "ApiKey", // Required. API key in string format for authentication.
  "APIUrl": "http://0.0.0.0:8080/stream-audio", // Required. TTS API URL in string format.
  "AudioFormat": "wav", // Optional. Expected output audio format in string format. For example, mp3, ogg_opus, pcm, and wav. Default value: wav. Currently, only pcm and wav are supported.
  "SampleRate": 16000,  // Optional. Audio sampling rate in integer format. Default value: 16000 (16 kHz). Recommended value: 16000.
  "AudioChannel": 1,    // Optional. Number of audio channels in integer format. Valid values: 1 and 2. Default value: 1.
}