chicogong/flowtts-byok-replicate

腾讯云 FlowTTS 语音合成 BYOK 封装。用户自带腾讯云凭证（SecretId、SecretKey、SdkAppId），调用 FlowTTS API 生成高质量中文语音。支持多种音色、语速、音量调节。输出 WAV 格式音频文件。

Public

0 runs

License

GitHub

Run chicogong/flowtts-byok-replicate with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
text	string		Text to synthesize (max 2000 characters)
secret_id	string		Tencent Cloud SecretId (BYOK)
secret_key	string		Tencent Cloud SecretKey (BYOK)
sdk_app_id	integer		Tencent Cloud TRTC SdkAppId (BYOK)
voice_id	string	v-female-R2s4N9qJ	Voice ID (e.g., v-female-R2s4N9qJ)
speed	number	1 Min: 0.5 Max: 2	Speech speed [0.5, 2.0]
volume	number	1 Max: 10	Volume [0, 10]
pitch	integer	0 Min: -12 Max: 12	Pitch adjustment [-12, 12] semitones
language	None	zh	Language: zh/en/yue/ja/ko/auto
sample_rate	None	24000	Audio sample rate: 16000 or 24000 Hz
timeout	integer	120 Min: 10 Max: 300	Request timeout in seconds [10, 300]

{
  "type": "object",
  "title": "Input",
  "required": [
    "text",
    "secret_id",
    "secret_key",
    "sdk_app_id"
  ],
  "properties": {
    "text": {
      "type": "string",
      "title": "Text",
      "x-order": 0,
      "description": "Text to synthesize (max 2000 characters)"
    },
    "pitch": {
      "type": "integer",
      "title": "Pitch",
      "default": 0,
      "maximum": 12,
      "minimum": -12,
      "x-order": 7,
      "description": "Pitch adjustment [-12, 12] semitones"
    },
    "speed": {
      "type": "number",
      "title": "Speed",
      "default": 1,
      "maximum": 2,
      "minimum": 0.5,
      "x-order": 5,
      "description": "Speech speed [0.5, 2.0]"
    },
    "volume": {
      "type": "number",
      "title": "Volume",
      "default": 1,
      "maximum": 10,
      "minimum": 0,
      "x-order": 6,
      "description": "Volume [0, 10]"
    },
    "timeout": {
      "type": "integer",
      "title": "Timeout",
      "default": 120,
      "maximum": 300,
      "minimum": 10,
      "x-order": 10,
      "description": "Request timeout in seconds [10, 300]"
    },
    "language": {
      "enum": [
        "zh",
        "en",
        "yue",
        "ja",
        "ko",
        "auto"
      ],
      "type": "string",
      "title": "language",
      "description": "Language: zh/en/yue/ja/ko/auto",
      "default": "zh",
      "x-order": 8
    },
    "voice_id": {
      "type": "string",
      "title": "Voice Id",
      "default": "v-female-R2s4N9qJ",
      "x-order": 4,
      "description": "Voice ID (e.g., v-female-R2s4N9qJ)"
    },
    "secret_id": {
      "type": "string",
      "title": "Secret Id",
      "format": "password",
      "x-order": 1,
      "writeOnly": true,
      "description": "Tencent Cloud SecretId (BYOK)",
      "x-cog-secret": true
    },
    "sdk_app_id": {
      "type": "integer",
      "title": "Sdk App Id",
      "x-order": 3,
      "description": "Tencent Cloud TRTC SdkAppId (BYOK)"
    },
    "secret_key": {
      "type": "string",
      "title": "Secret Key",
      "format": "password",
      "x-order": 2,
      "writeOnly": true,
      "description": "Tencent Cloud SecretKey (BYOK)",
      "x-cog-secret": true
    },
    "sample_rate": {
      "enum": [
        16000,
        24000
      ],
      "type": "integer",
      "title": "sample_rate",
      "description": "Audio sample rate: 16000 or 24000 Hz",
      "default": 24000,
      "x-order": 9
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}