Text to Speech API

Overview

Text-to-Speech API (TTS API)

Reverie's TTS (Text-to-Speech) is a solution that turns text into lifelike speech, allowing you to create applications that talk in multiple Indic languages and build comprehensive speech-enabled products.

The Reverie TTS service will offer neural Text-to-Speech voices, delivering innovative enhancements in speech quality through state-of-the-art machine learning approaches. You can select the ideal voice and tone to build the natural and human-like speech-enabled applications in the market to enable the interactive customer experience.

Supporting Languages

The TTS solution will understand popularly used ten languages using customizable voice and offer services to all the domains like Telecom, Banking, Entertainment, etc.:

  1. Hindi

  1. Marathi

  1. Odia

  1. Bengali

  1. Tamil

  1. Kannada

  1. Telugu

  1. Malayalam

  1. Gujarati

  1. Indian English

  1. Assamese

  1. Punjabi

Note: Our Research and Development team is continuously working to enable all the leading Indian languages on the Text-to-Speech platform with new voices across all the languages and strive to enhance the existing model’s accuracy.

Code-Mix Support

Reverie's Text-to-Speech feature caters to mixed text, meaning it can seamlessly read aloud content that includes English/Roman script in Indian languages.

Key Features

Reverie TTS API delivers remarkable robust features that effectively serve consumers in their native Indian language:

Faster than Real-time Speech Synthesis

The TTS API will swiftly synthesize the speech output, consuming less time than the time consumed to speak in real-time. This enables real-time user experience for your users using the application.

Customize the Speech Model

Train the text-to-speech solution to suit your requirements. The Reverie TTS will support lexicons and SSML tags, which allow you to manage the speech aspects like volume, pitch, speed rate, the pronunciation of words with context, etc.

Text and SSML Support

Customize your speech with SSML tags that allow you to add pauses, numbers, date and time formatting, and other pronunciation instructions.

High-Quality & Accurate Pronunciation

Attune your speech with SSML tags that allow you to add pauses, numbers, date and time formatting, and other pronunciation instructions, enabling you to deliver an accurate and high-quality voice-output.

Optimize Your Speech Output

You can choose from various sampling rates to optimize bandwidth and audio quality for your application. The Reverie TTS supports WAV, OGG, MP3, FLAC, Ogg Opus, and PCM audio formats with sampling rates ranging from 8kHz, 16kHz, 22.05kHz, 24kHz, 44.1kHz, and 48kHz.

Branded Custom Voices

We work with you on your voice requirements, select voice characteristics, and create and test your voice until it's ready to stand out of the crowd.

Benefits of Reverie TTS

Reverie’s TTS builds a comprehensive speech application as it is empowered with:

  • Extensive depository of lifelike voices

  • AI-optimized text processing

  • Dedicated support for multiple Indic languages

  • Allows customization to create unique voice personas

PreviousAPI MessagesNextSetup

Last updated