Feat/tts streaming (#994)

* wip

* add TtsStreamingBuffer class to abstract handling of streaming tokens

* wip

* add throttling support

* support background ttsStream (#995)

* wip

* add TtsStreamingBuffer class to abstract handling of streaming tokens

* wip

* support background ttsStream

* wip

---------

Co-authored-by: Dave Horton <daveh@beachdognet.com>

* wip

* dont send if we have nothing to send

* initial testing with cartesia

* wip

---------

Co-authored-by: Hoan Luu Huu <110280845+xquanluu@users.noreply.github.com>

lib/tasks/config.js

@@ -16,7 +16,8 @@ class TaskConfig extends Task {
       'fillerNoise',
       'actionHookDelayAction',
       'boostAudioSignal',
-      'vad'
+      'vad',
+      'ttsStream'
     ].forEach((k) => this[k] = this.data[k] || {});
 
     if ('notifyEvents' in this.data) {
@@ -45,6 +46,12 @@ class TaskConfig extends Task {
       };
       delete this.transcribeOpts.enable;
     }
+    if (this.ttsStream.enable) {
+      this.sayOpts = {
+        verb: 'say',
+        stream: true
+      };
+    }
 
     if (this.data.reset) {
       if (typeof this.data.reset === 'string') this.data.reset = [this.data.reset];
@@ -75,6 +82,7 @@ class TaskConfig extends Task {
   get hasVad() { return Object.keys(this.vad).length; }
   get hasFillerNoise() { return Object.keys(this.fillerNoise).length; }
   get hasReferHook() { return Object.keys(this.data).includes('referHook'); }
+  get hasTtsStream() { return Object.keys(this.ttsStream).length; }
 
   get summary() {
     const phrase = [];
@@ -106,6 +114,9 @@ class TaskConfig extends Task {
     if (this.onHoldMusic) phrase.push(`onHoldMusic: ${this.onHoldMusic}`);
     if ('boostAudioSignal' in this.data) phrase.push(`setGain ${this.data.boostAudioSignal}`);
     if (this.hasReferHook) phrase.push('set referHook');
+    if (this.hasTtsStream) {
+      phrase.push(`${this.ttsStream.enable ? 'enable' : 'disable'} ttsStream`);
+    }
     return `${this.name}{${phrase.join(',')}}`;
   }
 
@@ -305,6 +316,22 @@ class TaskConfig extends Task {
     if (this.hasReferHook) {
       cs.referHook = this.data.referHook;
     }
+
+    if (this.ttsStream.enable && this.sayOpts) {
+      this.sayOpts.synthesizer = this.hasSynthesizer ? this.synthesizer : {
+        vendor: cs.speechSynthesisVendor,
+        language: cs.speechSynthesisLanguage,
+        voice: cs.speechSynthesisVoice,
+        ...(cs.speechSynthesisLabel && {
+          label: cs.speechSynthesisLabel
+        })
+      };
+      this.logger.info({opts: this.gatherOpts}, 'Config: enabling ttsStream');
+      cs.enableBackgroundTtsStream(this.sayOpts);
+    } else if (!this.ttsStream.enable) {
+      this.logger.info('Config: disabling ttsStream');
+      cs.disableTtsStream();
+    }
   }
 
   async kill(cs) {