zf-kbot/breeze-tts | API reference

Public

2 runs

Run zf-kbot/breeze-tts 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 speak in Chinese or English.
instruction	string		Optional voice description or delivery direction. Match the text language.
ref_audio	string		Optional clean reference recording. Requires ref_text.
ref_text	string		Exact transcript of the entire reference recording.
cfg_scale	number	1 Min: 0.01 Max: 10	Use 1 for plain speech/cloning; try 4 when using instruction.
seed	integer	42 Max: 4294967295	Random seed.
max_new_tokens	integer	1500 Min: 1	Generation limit in codec frames (about 12.5 frames per second).

{
  "type": "object",
  "title": "Input",
  "required": [
    "text"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "default": 42,
      "maximum": 4294967295,
      "minimum": 0,
      "x-order": 5,
      "description": "Random seed."
    },
    "text": {
      "type": "string",
      "title": "Text",
      "x-order": 0,
      "description": "Text to speak in Chinese or English."
    },
    "ref_text": {
      "type": "string",
      "title": "Ref Text",
      "default": "",
      "x-order": 3,
      "description": "Exact transcript of the entire reference recording."
    },
    "cfg_scale": {
      "type": "number",
      "title": "Cfg Scale",
      "default": 1,
      "maximum": 10,
      "minimum": 0.01,
      "x-order": 4,
      "description": "Use 1 for plain speech/cloning; try 4 when using instruction."
    },
    "ref_audio": {
      "type": "string",
      "title": "Ref Audio",
      "format": "uri",
      "x-order": 2,
      "nullable": true,
      "description": "Optional clean reference recording. Requires ref_text."
    },
    "instruction": {
      "type": "string",
      "title": "Instruction",
      "default": "",
      "x-order": 1,
      "description": "Optional voice description or delivery direction. Match the text language."
    },
    "max_new_tokens": {
      "type": "integer",
      "title": "Max New Tokens",
      "default": 1500,
      "minimum": 1,
      "x-order": 6,
      "description": "Generation limit in codec frames (about 12.5 frames per second)."
    }
  }
}

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"
}