Started google cloud tests

frontend/react/src/audio/audiomanager.ts

@@ -158,8 +158,6 @@ export class AudioManager {
       this.#devices = devices;
       AudioManagerDevicesChangedEvent.dispatch(devices);
     });
-
-    this.#startSpeechRecognition();
   }
 
   stop() {
@@ -330,30 +328,4 @@ export class AudioManager {
 
     if (this.#socket?.readyState == 1) this.#socket?.send(new Uint8Array([AudioMessageType.settings, ...Buffer.from(JSON.stringify(message), "utf-8")]));
   }
-
-  #startSpeechRecognition() {
-    const grammar =
-      "#JSGF V1.0; grammar colors; public <color> = aqua | azure | beige | bisque | black | blue | brown | chocolate | coral | crimson | cyan | fuchsia | ghostwhite | gold | goldenrod | gray | green | indigo | ivory | khaki | lavender | lime | linen | magenta | maroon | moccasin | navy | olive | orange | orchid | peru | pink | plum | purple | red | salmon | sienna | silver | snow | tan | teal | thistle | tomato | turquoise | violet | white | yellow ;";
-    //@ts-ignore
-    const recognition = new window.webkitSpeechRecognition();
-    //@ts-ignore
-    const speechRecognitionList = new window.webkitSpeechGrammarList();
-    speechRecognitionList.addFromString(grammar, 1);
-    recognition.grammars = speechRecognitionList;
-    recognition.continuous = true;
-    recognition.lang = "en-US";
-    recognition.interimResults = true;
-    //recognition.maxAlternatives = 1;
-
-    const diagnostic = document.querySelector(".output");
-    const bg = document.querySelector("html");
-    recognition.start();
-
-
-    recognition.onresult = (event) => {
-      const color = event.results[0][0].transcript;
-      diagnostic.textContent = `Result received: ${color}`;
-      bg.style.backgroundColor = color;
-    };
-  }
 }

frontend/react/src/audio/texttospeechsource.ts

@@ -26,7 +26,7 @@ export class TextToSpeechSource extends AudioSource {
       body: JSON.stringify({ text }), // Send the data in JSON format
     };
 
-    fetch(getApp().getExpressAddress() + `/api/texttospeech/generate`, requestOptions)
+    fetch(getApp().getExpressAddress() + `/api/speech/generate`, requestOptions)
       .then((response) => {
         if (response.status === 200) {
           console.log(`Text to speech generate correctly`);

frontend/server/package.json

@@ -10,6 +10,7 @@
   },
   "private": true,
   "dependencies": {
+    "@google-cloud/speech": "^6.7.0",
     "appjs": "^0.0.20",
     "appjs-win32": "^0.0.19",
     "body-parser": "^1.20.2",

frontend/server/src/app.ts

@@ -27,7 +27,7 @@ module.exports = function (configLocation, viteProxy) {
       "databases"
     )
   );
-  const textToSpeechRouter = require("./routes/api/texttospeech")();
+  const speechRouter = require("./routes/api/speech")();
 
   /* Load the config and create the express app */
   let config = {};
@@ -76,12 +76,12 @@ module.exports = function (configLocation, viteProxy) {
   app.use("/api/airbases", airbasesRouter);
   app.use("/api/elevation", elevationRouter);
   app.use("/api/databases", databasesRouter);
-  app.use("/api/texttospeech", textToSpeechRouter);
+  app.use("/api/speech", speechRouter);
   app.use("/resources", resourcesRouter);
   app.use("/express/api/airbases", airbasesRouter);
   app.use("/express/api/elevation", elevationRouter);
   app.use("/express/api/databases", databasesRouter);
-  app.use("/express/api/texttospeech", textToSpeechRouter);
+  app.use("/express/api/speech", speechRouter);
   app.use("/express/resources", resourcesRouter);
 
   /* Set default index */

frontend/server/src/routes/api/speech.ts

@@ -0,0 +1,47 @@
+import express = require("express");
+import fs = require("fs");
+var gtts = require("node-gtts")("en");
+
+const router = express.Router();
+
+module.exports = function () {
+  router.put("/generate", (req, res, next) => {
+    res.set({ "Content-Type": "audio/mpeg" });
+    gtts.stream(req.body.text).pipe(res);
+  });
+
+  router.get("/recognize", (req, res, next) => {
+    //// Imports the Google Cloud client library
+    //const speech = require("@google-cloud/speech");
+//
+    //// Creates a client
+    //const client = new speech.SpeechClient();
+//
+    //// The path to the remote LINEAR16 file
+    //const gcsUri = "gs://cloud-samples-data/speech/brooklyn_bridge.raw";
+//
+    //// The audio file's encoding, sample rate in hertz, and BCP-47 language code
+    //const audio = {
+    //  uri: gcsUri,
+    //};
+    //const config = {
+    //  encoding: "LINEAR16",
+    //  sampleRateHertz: 16000,
+    //  languageCode: "en-US",
+    //};
+    //const request = {
+    //  audio: audio,
+    //  config: config,
+    //};
+//
+    //// Detects speech in the audio file
+    //client.recognize(request).then((response) => {
+    //  const transcription = response.results
+    //    .map((result) => result.alternatives[0].transcript)
+    //    .join("\n");
+    //  console.log(`Transcription: ${transcription}`);
+    //});
+  });
+
+  return router;
+};

frontend/server/src/routes/api/texttospeech.ts

@@ -1,14 +0,0 @@
-import express = require('express');
-import fs = require('fs');
-var gtts = require('node-gtts')('en');
-
-const router = express.Router();
-
-module.exports = function () {
-    router.put( "/generate", ( req, res, next ) => {        
-        res.set({'Content-Type': 'audio/mpeg'});
-        gtts.stream(req.body.text).pipe(res);
-    });
-
-    return router; 
-}