Introduction
Welcome to the Papla Media API documentation! Our API enables developers to integrate high-quality, natural-sounding text-to-speech capabilities into their applications.
What is the API?
The Papla Media API allows you to convert text into speech using state-of-the-art AI models. Whether you’re building an accessibility tool, a virtual assistant, or an interactive application, our API provides fast and accurate speech synthesis.
Key Features
- High-Quality Speech – Generate natural, human-like voices.
- Voice Cloning – Clone any voice from just 10 seconds of audio.
- Real-Time Processing – Get fast and responsive audio output.
- Standard & Streaming TTS API – Choose between normal text-to-speech conversion or streaming for low-latency applications.
How to Get Started
- Go to the Text To Speech Stream endpoint.
- Enter the required parameters:
- papla-api-key – Your authorization token.
- voice_id – The ID of the voice you want to use.
- text – The input text to be converted into speech.
- Send a request to generate streaming audio output.
- Need a Papla API key?
Get one for free by signing up for a free trial.
- Want to explore available voices?
Go to the Get Voices endpoint and send a request to retrieve voice samples and their corresponding IDs.