Speech API

Overview

The Speech API provides two main functionalities: Text-to-Speech and Speech-to-Text. These endpoints enable seamless conversion between text and audio formats, making them useful for accessibility, voice interactions, and content creation.

Endpoints

1. Text-to-Speech

Endpoint: /text-to-speech

• Method: POST
• Description: Converts text into an audio file using a specified language and voice type.

Request Body

{
  "text": "Hello, how can I assist you?",
  "language": "en-US",
}

2. Speech-to-Text

Endpoint: /speech-to-text

• Method: POST
• Description: Converts an audio file into text. You can optionally specify the language of the audio using a URL parameter.

Request Requirements

• Request Type: multipart/form-data
• Request Body: Contains a single key-value pair:
  • Key: audioFile
  • Value: The audio file (.wav, .mp3, etc.) to be transcribed.
• Optional URL Parameter: language (default: en-US)