TsgcTextToSpeechGoogle synthesises speech with Google Cloud Text-to-Speech. It signs a service account JWT, requests the audio, decodes it to a file and plays it through the audio player you assign, so a wide voice and language catalogue is a property away.
A Google Cloud speech backend. Paste the service account JSON into the options, choose the language, gender and voice, and call one method.
TsgcTextToSpeechGoogle
Google Cloud speech synthesis
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.
Provide the service account credentials, pick a voice, link an audio player.
uses
sgcAI, sgcAI_TextToSpeech_Google, sgcAI_AudioPlayer_MCI;
var
oTTS: TsgcTextToSpeechGoogle;
begin
oTTS := TsgcTextToSpeechGoogle.Create(nil);
oTTS.AudioPlayer := sgcAudioPlayerMCI1;
// The service account JSON, pasted as-is.
oTTS.GoogleOptions.Settings.LoadFromFile('service-account.json');
oTTS.GoogleOptions.Language := 'en-US';
oTTS.GoogleOptions.VoiceId := 'en-US-Neural2-C';
oTTS.GoogleOptions.AudioEncoding := 'MP3';
oTTS.GoogleOptions.FileName := 'speech.mp3';
oTTS.TextToSpeech('The order has been shipped.');
end;// includes: sgcAI.hpp, sgcAI_TextToSpeech_Google.hpp
TsgcTextToSpeechGoogle *oTTS = new TsgcTextToSpeechGoogle(NULL);
oTTS->AudioPlayer = sgcAudioPlayerMCI1;
oTTS->GoogleOptions->Settings->LoadFromFile("service-account.json");
oTTS->GoogleOptions->Language = "en-US";
oTTS->GoogleOptions->VoiceId = "en-US-Neural2-C";
oTTS->TextToSpeech("The order has been shipped.");The members you reach for most often.
Settings holds the service account JSON, Language and VoiceId select the voice, Gender picks a default voice when no id is given, and AudioEncoding and FileName control the synthesised audio.
AudioPlayer plays the synthesised file. Assign a TsgcAudioPlayerMCI and playback starts as soon as the response arrives.
The component builds and signs a JWT from the private key in the service account, then caches the access token until it expires, so a long-running application does not re-authenticate on every phrase.
TextToSpeech(aText) performs the whole cycle: request, decode, write, play and clean up the temporary file.
OnStart and OnStop bracket the operation, which is what lets the chatbot and translator components resume recording once the reply has been spoken.
The same interface as the system and Amazon speech components, so the chatbot, translator and assistant accept any of them without code changes.
Authoritative sources for the services and protocols this component uses.
| Online HelpFull API reference and usage guide for the sgcAI components. | Open | |
| All sgcAI ComponentsBrowse the full feature matrix of all 15 components. | Open | |
| Download Free TrialSynthesise speech with your own Google Cloud project. | Open | |
| PricingSingle, Team and Site licenses, full source code, no base product required. | Open |