Class TextToSpeech

The TextToSpeech class provides functionalities for converting text to speech using the TikTok and Deepgram APIs.

Index

Constructors

Properties

apiToken logger sessionId

Methods

Constructors

constructor

new TextToSpeech(components): TextToSpeech
Constructs a new TextToSpeech instance.
Parameters
- components: TTSComponents
  Components to initialize the TextToSpeech instance.
Returns TextToSpeech
Throws
If API key or SessionID is missing.
- Defined in tts.ts:88

Properties

apiToken

apiToken: string

API token for authentication with the text-to-speech services

logger

logger: boolean

Flag to enable or disable logging

sessionId

sessionId: string

Session ID for TikTok text-to-speech API

Methods

createSpeech

createSpeech(args): Promise<undefined | string>
Generates speech audio from the provided text using the specified API.
Parameters
- args: CreateSpeech
  Arguments for generating the speech.
Returns Promise<undefined | string>
A Promise that resolves to the file path of the generated audio file or undefined if an error occurs.
- Defined in tts.ts:105