TextToSpeechHistoryObject

A stored text-to-speech generation.

Example Usage

import { TextToSpeechHistoryObject } from "@meetkai/mka1/models/components";

let value: TextToSpeechHistoryObject = {
  id: "<id>",
  object: "speech.tts",
  text: "<value>",
  language: "<value>",
  detectedLanguage: "<value>",
  model: "2",
  providerId: "<id>",
  format: "<value>",
  audioBytes: 537031,
  characters: 273565,
  streaming: true,
  metadata: {
    "key": "<value>",
  },
  createdAt: 239871,
};

Fields

Field	Type	Required	Description
id	string	✔️	Unique identifier for the history item.
object	"speech.tts"	✔️	The object type, always 'speech.tts'.
text	string	✔️	The input text that was synthesized.
language	string	✔️	The requested language ('auto' or an ISO 639-1 code).
detectedLanguage	string	✔️	The language actually used for synthesis.
model	string	✔️	The TTS model used.
providerId	string	✔️	The provider that produced the audio.
format	string	✔️	Audio format of the stored output (wav, mp3, or pcm).
audioBytes	number	✔️	Size of the generated audio in bytes.
characters	number	✔️	Number of characters in the input text.
streaming	boolean	✔️	Whether the audio was produced via the streaming endpoint.
metadata	Record<string, any>	✔️	Arbitrary metadata stored with the item.
createdAt	number	✔️	Unix timestamp (seconds) when the item was created.