Skip to main content

Getting Started

Introduction​

Whisperly TTS is an advanced text-to-speech system that converts your text inputs into natural-sounding audio. It is designed to be simple to use, enabling you to generate voice files from text while customizing various parameters such as speed and language.

How It Works​

  1. Submit Text & Audio Reference:
    Provide the text to be converted along with an optional speaker voice sample.
  2. Processing:
    The system processes your request and generates an audio file based on your specifications.
  3. Receive the Generated Voice:
    Once processed, you receive an output audio file that reflects the generated voice based on your input text and settings.

Features​

  • Natural Voice Synthesis:
    Generates high-quality, natural-sounding audio.
  • Customizable Parameters:
    Control the speed, language, and sentence splitting options.
  • Speaker Adaptation:
    Optionally include a speaker sample (WAV file) to mimic a particular voice.
  • Easy Integration:
    Access via RESTful API endpoints using simple HTTP calls.
  • Secure Access:
    Uses API key-based authentication to ensure secure operations. Every letter is 0.25 credit.