System Text to Speech Component — sgcAI | eSeGeCe

Text to Speech (System)

TsgcTextToSpeechSystem speaks text through the speech engine already present on the machine. There is no API key to manage, no per-character billing and no network call, which makes it the right default for offline and on-premises applications.

TsgcTextToSpeechSystem

The simplest of the three speech components. Call one method with a string and the machine speaks it, synchronously, with start and stop events around the call.

Component class

TsgcTextToSpeechSystem

Purpose

Offline speech synthesis

Platforms

Win32 and Win64

sgcAI is self-contained. This component ships inside sgcAI together with the sgcWebSockets Core runtime it is built on, so there is no base license to buy.

Speak a string

No configuration, no credentials. Assign it to a chatbot, translator or assistant and it becomes their voice.

uses
  sgcAI, sgcAI_TextToSpeech_System;

var
  oTTS: TsgcTextToSpeechSystem;
begin
  oTTS := TsgcTextToSpeechSystem.Create(nil);
  oTTS.TextToSpeech('The order has been shipped.');

  // Used as the voice of a chatbot:
  sgcAIOpenAIChatBot1.TextToSpeech := oTTS;
end;
// includes: sgcAI.hpp, sgcAI_TextToSpeech_System.hpp

TsgcTextToSpeechSystem *oTTS = new TsgcTextToSpeechSystem(NULL);
oTTS->TextToSpeech("The order has been shipped.");

// Used as the voice of a chatbot:
sgcAIOpenAIChatBot1->TextToSpeech = oTTS;

Key properties & methods

The members you reach for most often.

TextToSpeech

TextToSpeech(aText) speaks the string through the system voice. The call is synchronous, so it returns once speech has finished.

No audio player needed

Unlike the cloud speech components, this one produces no audio file and needs no AudioPlayer link. Nothing is written to disk.

No credentials

There is no API key, no quota and no cost per character, which matters when a component speaks continuously in a kiosk or a monitoring application.

Lifecycle

OnStart and OnStop bracket the call, which is what lets the chatbot components restart microphone capture the moment the answer has finished.

Voice selection

The voice, rate and volume come from the speech settings of the machine, so an operator can change them without a rebuild.

Interchangeable

It shares its interface with the Google and Amazon speech components, so switching to a cloud voice later is a change of component, not a change of code.

Keep exploring

Online HelpFull API reference and usage guide for the sgcAI components.
All sgcAI ComponentsBrowse the full feature matrix of all 15 components.
Download Free TrialGive your application a voice with no account to create.
PricingSingle, Team and Site licenses, full source code, no base product required.
Best value: All-AccessEvery eSeGeCe product, Premium Support included, from €1,059/year.
See All-Access pricing

Ready to Get Started?

Download the free trial and make your application speak.