bump version and minor changes

fix: use synthesized audio data directly from microsoft sdk

lib/synth-audio.js

@@ -2,14 +2,12 @@ const assert = require('assert');
 const fs = require('fs');
 const bent = require('bent');
 const ttsGoogle = require('@google-cloud/text-to-speech');
-//const Polly = require('aws-sdk/clients/polly');
 const { PollyClient, SynthesizeSpeechCommand } = require('@aws-sdk/client-polly');
 
 const sdk = require('microsoft-cognitiveservices-speech-sdk');
 const TextToSpeechV1 = require('ibm-watson/text-to-speech/v1');
 const { IamAuthenticator } = require('ibm-watson/auth');
 const {
-  AudioConfig,
   ResultReason,
   SpeechConfig,
   SpeechSynthesizer,
@@ -302,8 +300,7 @@ const synthMicrosoft = async(logger, {
       if (!content.startsWith('<speak')) content = `<speak>${text}</speak>`;
     }
     speechConfig.speechSynthesisOutputFormat = SpeechSynthesisOutputFormat.Audio16Khz32KBitRateMonoMp3;
-    const config = AudioConfig.fromAudioFileOutput(filePath);
-    const synthesizer = new SpeechSynthesizer(speechConfig, config);
+    const synthesizer = new SpeechSynthesizer(speechConfig);
 
     if (content.startsWith('<speak>')) {
       /* microsoft enforces some properties and uses voice xml element so if the user did not supply do it for them */
@@ -329,11 +326,8 @@ const synthMicrosoft = async(logger, {
               break;
             case ResultReason.SynthesizingAudioCompleted:
               stats.increment('tts.count', ['vendor:microsoft', 'accepted:yes']);
+              resolve(result.audioData);
               synthesizer.close();
-              fs.readFile(filePath, (err, data) => {
-                if (err) return reject(err);
-                resolve(data);
-              });
               break;
             default:
               logger.info({result}, 'synthAudio: (Microsoft) unexpected result');
@@ -444,7 +438,6 @@ const synthNvidia = async(client, logger, {credentials, stats, language,  voice,
   request.setText(text);
 
   return new Promise((resolve, reject) => {
-    console.log(`language ${language} voice ${voice} model ${model} text ${text}`);
     rivaClient.synthesize(request, (err, response) => {
       if (err) {
         console.error(err);

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jambonz/speech-utils",
-  "version": "0.0.8",
+  "version": "0.0.10",
   "description": "TTS-related speech utilities for jambonz",
   "main": "index.js",
   "author": "Dave Horton",
@@ -24,18 +24,18 @@
   },
   "homepage": "https://github.com/jambonz/speech-utils#readme",
   "dependencies": {
-    "@aws-sdk/client-polly": "^3.276.0",
-    "@google-cloud/text-to-speech": "^4.2.0",
-    "@grpc/grpc-js": "^1.8.7",
-    "@jambonz/realtimedb-helpers": "^0.6.3",
-    "aws-sdk": "^2.1310.0",
+    "@aws-sdk/client-polly": "^3.303.0",
+    "@google-cloud/text-to-speech": "^4.2.1",
+    "@grpc/grpc-js": "^1.8.13",
+    "@jambonz/promisify-redis": "^0.0.6",
     "bent": "^7.3.12",
     "debug": "^4.3.4",
-    "google-protobuf": "^3.21.2",
-    "ibm-watson": "^7.1.2",
     "form-urlencoded": "^6.1.0",
-    "microsoft-cognitiveservices-speech-sdk": "^1.25.0",
-    "undici": "^5.19.1"
+    "google-protobuf": "^3.21.2",
+    "ibm-watson": "^8.0.0",
+    "microsoft-cognitiveservices-speech-sdk": "^1.26.0",
+    "redis": "^3.1.2",
+    "undici": "^5.21.0"
   },
   "devDependencies": {
     "config": "^3.3.9",