Closed Ty-lerCox closed 1 year ago
This almost works. The tracks overlap with one another.
function CN_SayOutLoud(text) {
console.log(text);
if (!text || CN_SPEAKING_DISABLED) {
if (CN_SPEECH_REC_SUPPORTED && CN_SPEECHREC && !CN_IS_LISTENING && !CN_PAUSED && !CN_SPEECHREC_DISABLED) CN_SPEECHREC.start();
clearTimeout(CN_TIMEOUT_KEEP_SPEECHREC_WORKING);
CN_TIMEOUT_KEEP_SPEECHREC_WORKING = setTimeout(CN_KeepSpeechRecWorking, 100);
return;
}
// Are we speaking?
if (CN_SPEECHREC) {
clearTimeout(CN_TIMEOUT_KEEP_SPEECHREC_WORKING);
CN_SPEECHREC.stop();
}
// Let's speak out loud
console.log("Saying out loud: " + text);
AWS.config.update({
accessKeyId: "",
secretAccessKey: "",
region: "us-east-1"
});
var polly = new AWS.Polly();
var params = {
OutputFormat: "mp3",
Text: text,
VoiceId: "Joanna"
};
polly.synthesizeSpeech(params, function(err, data) {
if (err) {
console.log(err, err.stack);
} else {
var uInt8Array = new Uint8Array(data.AudioStream);
var arrayBuffer = uInt8Array.buffer;
var blob = new Blob([arrayBuffer]);
var audioElement = new Audio();
audioElement.src = URL.createObjectURL(blob);
audioElement.play();
}
});
}```
https://github.com/Ty-lerCox/talk-to-chatgpt
Here is a hacky implementation of it.
Would you kindly record a quick video or something so we can understand how much of an improvement it is over the default voices?
Hello there,
I have added ElevenLabs API support in v2.6.0. It's been requested by a lot of people, and I believe it's as good as (if not better than) Amazon Polly.
Considering this, do you still feel that Amazon Polly integration is useful? If not, I will close the issue.
closed due to inactivity. Feel free to reopen later if necessary
I have pulled down the project and attempted to add this myself, but Amazon's Polly API generates very pleasant speech-to-text.
I wish there were an option or adding an AWS API key and selecting an Amazon Polly's voice.