Speakatoo - Speech to Text API Documentation

Speakatoo Speech-to-Text API Documentation

This document provides full integration details for the Speakatoo Speech‑to‑Text API.

Overview

The Speakatoo Speech-to-Text API enables developers to upload audio files and receive accurate transcriptions. It supports multiple languages, minute-based usage deduction, and full logging into the user's dashboard.

This API is designed for real-time usage without queue or cron dependency.

Authentication

Speakatoo uses API-key–based authentication.

Include your API key in the header of every request:

X-API-KEY: your_api_key_here

Failure to include this header will result in a 403 error.

Endpoint

Method: multipart/form-data

Request Body Parameters

Required:

- file: Audio file to be transcribed

- file_language: Language code (ISO format)

- response_format: text | json

Optional:

- prompt: Provide context or instructions to improve transcription accuracy

POSTMAN SCREENSHOT

Supported Languages (Sample List)

Below is a sample list of supported languages:

{
  "status": true,
  "message": "Transcription generated successfully.",
  "data": {
    "file_language": "en",
    "response_format": "text",
    "transcripted_text": "Hello world",
    "transcripted_text_length": 11
  }
}

{
  "status": false,
  "message": "Insufficient Speech-to-Text minutes. Please recharge."
}