Text to Speech
Text-to-Speech (TTS) service converts text into audio data. It accomplishes this by dividing the inputted text into sentences, words, and phonemes. It then converts the divided segments into speech signals and synthesizes those signals into audio data.
TTS service by LG AI Platform supports the following features:
Analyzes text inputted by the user, examining pronunciation, syllables, phrases, context, parts of speech, etc.
|Advanced speech synthesis||
Learns and restores audio signals based on artificial neural network technology, and generates voice data using Vocoder.
|Fast response time||
Generates audio data as soon as the user inputs text.
Employs natural, human-like speech using the latest deep learning technology.
Supports Korean and English languages.
Allows the selection of voice gender according to user preferences.
|Speech speed control||
Offers five-speed levels to deliver speech output.
Customizes voice pitch according to user preferences.
Offers ten levels of volume control.
Adds sound effects such as robotization and echo to voices according to preferences.
All functions of TTS service are run on a server. TTS service receives text and JSON data as input, and generates audio data output.
Examples of Use
TTS service can be used in a variety of situations that require voice-based services. TTS service can also be used to assist the visually impaired, narrate audiobooks, or elevate the functions of any application that plays voice audio.
- Voice functionality for personal devices
TTS service can be used for a service that reads mobile texts to drivers.
- Voice functionality for home appliances
Refrigerators equipped with TTS service can read cooking recipes aloud.
- Navigation voice service
TTS service can enable a car navigation service to read directions to a destination entered into the system.