> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.aiola.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.aiola.ai/_mcp/server.

# Text to Speech

> Here you'll find information to get started with the Text to Speech API

## Overview

Our TTS model is a cutting-edge Text-to-Speech (TTS) system designed for natural, high-quality speech synthesis. It is optimized for enterprise applications, offering unmatched clarity, adaptability, and customization.

## Key Features

* **Jargon Word Pronunciation** – Users can provide an audio recording of how a specific word should be pronounced, and the model conditions on that input to ensure precise and natural-sounding speech synthesis.
* **Multi-Language & Multi-Voice Support** – Our TTS model supports multiple languages and voices, making it highly adaptable for global applications.
* **Low Latency** – Optimized for real-time speech generation, making it ideal for conversational AI, virtual assistants, and interactive voice applications.

## Why Jargon Pronunciation Matters for Enterprises

Accurate pronunciation is essential for industries that rely on domain-specific terminology, including:

* **Healthcare** – Correct pronunciation of medical terms, drug names, and procedures.
* **Legal** – Accurate vocalization of case law terminology and regulatory phrases.
* **Finance & Banking** – Proper pronunciation of company names, financial instruments, and industry-specific jargon.
* **Technology & Engineering** – Consistent pronunciation of product names, programming terms, and technical vocabulary.

For enterprises, consistent and natural pronunciation enhances brand trust, accessibility, and user experience, making our TTS model a powerful tool for automated voice applications, customer service, virtual assistants, and training materials.