TTS TikTok API

Welcome to the TTS TikTok API documentation! This API allows you to generate TikTok-style voices for your applications. Simply pass a JSON payload to the endpoint with the following format:

{
	"lang" : "string",
	"voice": "string",
	"text": "string"
}

JSON Payload Keys:

• lang (string, required): The language for the voice generation.
• voice (string, required): The TikTok-style voice to use.
• text (string, required): The text to be converted into speech (Max. characters is: 299).

Query Parameter

Before making the request to the endpoint, you must provide a query parameter named response. This parameter can have two possible values:

• “base64”: The API will return the audio data in Base64 format.
• “url”: The audio will be uploaded to a server, and the API will return the URL of the audio. Note that uploaded files are deleted after 30 days.

Supported Languages and Voices

The TTS TikTok API supports the following languages and their corresponding voices:

Response Format

The API will always return a JSON response in the following format:

{
	"data": "object or null",
	"errors": "array or null",
	"message": "string",
	"success": "boolean"
}

• data (object or null): The resulting data of the API call, if successful.
• errors (array or null): Any errors encountered during the API call.
• message (string): A message indicating the result of the API call.
• success (boolean): Indicates whether the API call was successful (true) or not (false).