add audio worklet

tests/audio.js

@@ -1,84 +1,38 @@
 
-const speech = require('@google-cloud/speech');
+// const speech = require('@google-cloud/speech');
 const portAudio = require('naudiodon');
 // const rs = fs.createReadStream('rawAudio.wav');
 
-// Creates a client
-const client = new speech.SpeechClient();
-
-const encoding = 'LINEAR16';
-const sampleRateHertz = 16000;
-const languageCode = 'en-US';
-
 const audioContainer = {
     input: '',
     buffers: []
 }
 
-const config = {
-  encoding: encoding,
-  sampleRateHertz: sampleRateHertz,
-  languageCode: languageCode,
-};
-
-/**
- * Note that transcription is limited to 60 seconds audio.
- * Use a GCS file for audio longer than 1 minute.
- */
-async function transcribeSpeech (audio) {
-  const request = {
-    config: config,
-    audio: audio,
-  };
-
-  // Detects speech in the audio file. This creates a recognition job that you
-  // can wait for now, or get its result later.
-  const [operation] = await client.longRunningRecognize(request);
-
-  // Get a Promise representation of the final result of the job
-  const [response] = await operation.promise();
-
-  const transcription = response.results
-    .map(result => result.alternatives[0].transcript)
-    .join('\n');
-  console.log(`Transcription: ${transcription}`);
-}
 
 let record = true;
 
 // Create an instance of AudioIO with inOptions (defaults are as below), which will return a ReadableStream
-const ia = new portAudio.AudioIO({
+const aio = new portAudio.AudioIO({
   inOptions: {
-    channelCount: 1,
-    sampleFormat: 16,
-    sampleRate: 16000,
-    deviceId: -1,
-    closeOnError: false,
+    channelCount: 2,
+    sampleFormat: portAudio.SampleFormat16Bit,
+    sampleRate: 44100,
+    deviceId: -1 // Use -1 or omit the deviceId to select the default device
   },
-});
-ia.setEncoding('base64');
-ia.start();
-ia.on('data', (chunk) => {
-    if (record) {
-        console.log('recording data');
-        audioContainer.input += chunk;
-    } else {
-        if (audioContainer.input.length) audioContainer.input = "";
-    }
+  outOptions: {
+    channelCount: 2,
+    sampleFormat: portAudio.SampleFormat16Bit,
+    sampleRate: 44100,
+    deviceId: -1 // Use -1 or omit the deviceId to select the default device
+  }
 });
 
-const ao = new portAudio.AudioIO({
-    outOptions: {
-        sampleFormat: 16,
-        channelCount: 1,
-        sampleRate: 16000,
-        deviceId: -1,
-        closeOnError: false,
-    }
-});
-ao.start();
 
-let counter = 0;
+aio.start()
+aio.read()
+aio.on('data', buf => console.log(buf.timestamp));
+
+const counter = 0;
 const tests = [];
 
 function testCallback() {
@@ -143,13 +97,6 @@ function bufSplit(input){
 }
 
 async function test() {
-    transcribeSpeech({
-        content: Buffer.from(audioContainer.input, 'base64')
-    });
-    tests.push(audioContainer.input)
-    counter++;
-    console.log('audio string length:', audioContainer.input.length)
-    console.log('buffers written: ', audioContainer.buffers.length)
 }
 
 setTimeout(async () => {
@@ -157,26 +104,6 @@ setTimeout(async () => {
     test()
 }, 4000);
 
-// setTimeout(() => {
-//     record = true;
-// }, 6000)
-//
-// setTimeout(async () => {
-//     record = false;
-//     test();
-// }, 9000);
-//
-// setTimeout(() => {
-//     record = true;
-// }, 11000)
-//
-// setTimeout(async () => {
-//     record = false;
-//     test();
-// }, 14000);
-//
 setTimeout(async () => {
-    ia.quit();
-    testCallback()
     return;
 }, 6000);

tests/transcribe.js

@@ -0,0 +1,38 @@
+
+const speech = require('@google-cloud/speech');
+
+// Creates a client
+const client = new speech.SpeechClient();
+
+const encoding = 'LINEAR16';
+const sampleRateHertz = 16000;
+const languageCode = 'en-US';
+
+const config = {
+  encoding: encoding,
+  sampleRateHertz: sampleRateHertz,
+  languageCode: languageCode,
+};
+
+/**
+ * Note that transcription is limited to 60 seconds audio.
+ * Use a GCS file for audio longer than 1 minute.
+ */
+async function transcribeSpeech (audio) {
+  const request = {
+    config: config,
+    audio: audio,
+  };
+
+  // Detects speech in the audio file. This creates a recognition job that you
+  // can wait for now, or get its result later.
+  const [operation] = await client.longRunningRecognize(request);
+
+  // Get a Promise representation of the final result of the job
+  const [response] = await operation.promise();
+
+  const transcription = response.results
+    .map(result => result.alternatives[0].transcript)
+    .join('\n');
+  console.log(`Transcription: ${transcription}`);
+}