Merge branch 'main' into fix/fd_1828

* put removeListner in a try/catch

* typo

lib/config.js

@@ -119,7 +119,7 @@ const ENCRYPTION_SECRET = process.env.ENCRYPTION_SECRET;
 const HTTP_POOL = process.env.HTTP_POOL && parseInt(process.env.HTTP_POOL);
 const HTTP_POOLSIZE = parseInt(process.env.HTTP_POOLSIZE, 10) || 10;
 const HTTP_PIPELINING = parseInt(process.env.HTTP_PIPELINING, 10) || 1;
-const HTTP_TIMEOUT = 10000;
+const HTTP_TIMEOUT = parseInt(process.env.JAMBONES_HTTP_TIMEOUT, 10) || 10000;
 const HTTP_PROXY_IP = process.env.JAMBONES_HTTP_PROXY_IP;
 const HTTP_PROXY_PORT = process.env.JAMBONES_HTTP_PROXY_PORT;
 const HTTP_PROXY_PROTOCOL = process.env.JAMBONES_HTTP_PROXY_PROTOCOL || 'http';
@@ -139,6 +139,11 @@ const JAMBONES_USE_FREESWITCH_TIMER_FD = process.env.JAMBONES_USE_FREESWITCH_TIM
 const JAMBONES_DIAL_SBC_FOR_REGISTERED_USER = process.env.JAMBONES_DIAL_SBC_FOR_REGISTERED_USER || false;
 const JAMBONES_MEDIA_TIMEOUT_MS = process.env.JAMBONES_MEDIA_TIMEOUT_MS || 0;
 const JAMBONES_MEDIA_HOLD_TIMEOUT_MS = process.env.JAMBONES_MEDIA_HOLD_TIMEOUT_MS || 0;
+const JAMBONES_WEBHOOK_ERROR_RETURN = parseInt(process.env.JAMBONES_WEBHOOK_ERROR_RETURN, 10) || 480;
+
+/* say / tts */
+const JAMBONES_SAY_CHUNK_SIZE = parseInt(process.env.JAMBONES_SAY_CHUNK_SIZE, 10) || 900;
+
 // jambonz
 const JAMBONES_TRANSCRIBE_EP_DESTROY_DELAY_MS =
   process.env.JAMBONES_TRANSCRIBE_EP_DESTROY_DELAY_MS;
@@ -231,5 +236,7 @@ module.exports = {
   JAMBONES_DIAL_SBC_FOR_REGISTERED_USER,
   JAMBONES_MEDIA_TIMEOUT_MS,
   JAMBONES_MEDIA_HOLD_TIMEOUT_MS,
+  JAMBONES_SAY_CHUNK_SIZE,
   JAMBONES_TRANSCRIBE_EP_DESTROY_DELAY_MS,
+  JAMBONES_WEBHOOK_ERROR_RETURN
 };

lib/http-routes/api/create-call.js

@@ -291,7 +291,7 @@ router.post('/',
             }, {
               ...(account.enable_debug_log && {level: 'debug'})
             });
-            app.requestor.logger = app.notifier.logger = sipLogger;
+            app.requestor.logger = app.notifier.logger = restDial.logger = sipLogger;
             const callInfo = new CallInfo({
               direction: CallDirection.Outbound,
               req: inviteReq,

lib/middleware.js

@@ -12,7 +12,8 @@ const RootSpan = require('./utils/call-tracer');
 const listTaskNames = require('./utils/summarize-tasks');
 const {
   JAMBONES_MYSQL_REFRESH_TTL,
-  JAMBONES_DISABLE_DIRECT_P2P_CALL
+  JAMBONES_DISABLE_DIRECT_P2P_CALL,
+  JAMBONES_WEBHOOK_ERROR_RETURN
 } = require('./config');
 const { createJambonzApp } = require('./dynamic-apps');
 const { decrypt } = require('./utils/encrypt-decrypt');
@@ -112,6 +113,14 @@ module.exports = function(srf, logger) {
         req.locals.callingNumber = sipURIs[1];
       }
     }
+
+    // Feature server INVITE request pipelines taking time to finish,
+    // while connecting and fetch application from db and invoking webhook.
+    // call can be canceled without any handling, so we add a listener here
+    req.once('cancel', (sipMsg) => {
+      logger.info(`${callId} got CANCEL request`);
+      req.locals.canceled = true;
+    });
     next();
   }
 
@@ -362,13 +371,14 @@ module.exports = function(srf, logger) {
       });
       // if transferred call contains callInfo, let update original data to newly created callInfo in this instance.
       if (app.transferredCall && app.callInfo) {
-        const {direction, callerName, from, to, originatingSipIp, originatingSipTrunkName} = app.callInfo;
+        const {direction, callerName, from, to, originatingSipIp, originatingSipTrunkName, customerData} = app.callInfo;
         req.locals.callInfo.direction = direction;
         req.locals.callInfo.callerName = callerName;
         req.locals.callInfo.from = from;
         req.locals.callInfo.to = to;
         req.locals.callInfo.originatingSipIp = originatingSipIp;
         req.locals.callInfo.originatingSipTrunkName = originatingSipTrunkName;
+        if (customerData) req.locals.callInfo.customerData = customerData;
         delete app.callInfo;
       }
       next();
@@ -471,7 +481,7 @@ module.exports = function(srf, logger) {
         message: `${err?.message}`.trim()
       }).catch((err) => this.logger.info({err}, 'Error generating alert for parsing application'));
       logger.info({err}, `Error retrieving or parsing application: ${err?.message}`);
-      res.send(480, {headers: {'X-Reason': err?.message || 'unknown'}});
+      res.send(JAMBONES_WEBHOOK_ERROR_RETURN, {headers: {'X-Reason': err?.message || 'unknown'}});
       app.requestor.close(WS_CLOSE_CODES.GoingAway);
     }
   }

lib/session/call-session.js

@@ -504,7 +504,12 @@ class CallSession extends Emitter {
   }
 
   get isTtsStreamEnabled() {
-    return this.backgroundTaskManager.isTaskRunning('ttsStream');
+    // 1st background tts stream
+    return this.backgroundTaskManager.isTaskRunning('ttsStream') ||
+    // 2nd current task streaming tts
+    TaskName.Say === this.currentTask?.name && this.currentTask?.isStreamingTts ||
+    // 3rd nested verb is streaming tts
+    TaskName.Gather === this.currentTask?.name && this.currentTask.sayTask?.isStreamingTts;
   }
 
   get isListenEnabled() {
@@ -658,6 +663,15 @@ class CallSession extends Emitter {
     }
   }
 
+  // disableTtsCache
+  get disableTtsCache() {
+    return this._disableTtsCache || false;
+  }
+
+  set disableTtsCache(d) {
+    this._disableTtsCache = d;
+  }
+
   getTsStreamingVendor() {
     let v;
     if (this.currentTask?.isStreamingTts) {
@@ -918,7 +932,7 @@ class CallSession extends Emitter {
         this.logger.debug('CallSession:enableBackgroundTtsStream - ttsStream enabled');
       } else {
         this.logger.debug(
-          'CallSession:enableBackgroundTtsStream - ignoring request as call does not have required conditions');
+          'CallSession:enableBackgroundTtsStream - ignoring request; conditions not met (probably not using ws api)');
       }
     }  catch (err) {
       this.logger.info({err, say}, 'CallSession:enableBackgroundTtsStream - Error creating background tts stream task');
@@ -932,15 +946,25 @@ class CallSession extends Emitter {
     }
   }
   clearTtsStream() {
-    this.requestor?.request('tts:streaming-event', '/streaming-event', {event_type: 'user_interruption'})
-      .catch((err) => this.logger.info({err}, 'CallSession:clearTtsStream - Error sending user_interruption'));
-    this.ttsStreamingBuffer?.clear();
+    if (this.isTtsStreamEnabled) {
+      this.requestor?.request('tts:streaming-event', '/streaming-event', {event_type: 'user_interruption'})
+        .catch((err) => this.logger.info({err}, 'CallSession:clearTtsStream - Error sending user_interruption'));
+      this.ttsStreamingBuffer?.clear();
+    }
   }
 
   startTtsStream() {
     this.ttsStreamingBuffer?.start();
   }
 
+  stopTtsStream() {
+    if (this.isTtsStreamEnabled) {
+      this.requestor?.request('tts:streaming-event', '/streaming-event', {event_type: 'stream_closed'})
+        .catch((err) => this.logger.info({err}, 'CallSession:clearTtsStream - Error sending user_interruption'));
+      this.ttsStreamingBuffer?.stop();
+    }
+  }
+
   async enableBotMode(gather, autoEnable) {
     try {
       let task;
@@ -964,7 +988,7 @@ class CallSession extends Emitter {
       task.sticky = autoEnable;
       // listen to the bargein-done from background manager
       this.backgroundTaskManager.on('bargeIn-done', () => {
-        if (this.requestor instanceof WsRequestor) {
+        if (this.appIsUsingWebsockets) {
           try {
             this.kill(true);
           } catch (err) {}
@@ -1086,6 +1110,13 @@ class CallSession extends Emitter {
             deepgram_stt_use_tls: credential.deepgram_stt_use_tls
           };
         }
+        else if ('gladia' === vendor) {
+          return {
+            speech_credential_sid: credential.speech_credential_sid,
+            api_key: credential.api_key,
+            region: credential.region,
+          };
+        }
         else if ('soniox' === vendor) {
           return {
             speech_credential_sid: credential.speech_credential_sid,
@@ -1117,6 +1148,7 @@ class CallSession extends Emitter {
           return {
             api_key: credential.api_key,
             model_id: credential.model_id,
+            api_uri: credential.api_uri,
             options: credential.options
           };
         }
@@ -1165,6 +1197,15 @@ class CallSession extends Emitter {
             service_version: credential.service_version
           };
         }
+        else if ('houndify' === vendor) {
+          return {
+            speech_credential_sid: credential.speech_credential_sid,
+            client_id: credential.client_id,
+            client_key: credential.client_key,
+            user_id: credential.user_id,
+            houndify_server_uri: credential.houndify_server_uri
+          };
+        }
         else if ('deepgramflux' === vendor) {
           return {
             speech_credential_sid: credential.speech_credential_sid,
@@ -1214,9 +1255,10 @@ class CallSession extends Emitter {
       }
       else {
         writeAlerts({
-          alert_type: AlertType.STT_NOT_PROVISIONED,
+          alert_type: type === 'tts' ? AlertType.TTS_NOT_PROVISIONED : AlertType.STT_NOT_PROVISIONED,
           account_sid: this.accountSid,
           vendor,
+          label,
           target_sid: this.callSid
         }).catch((err) => this.logger.error({err}, 'Error writing tts alert'));
       }
@@ -1247,6 +1289,7 @@ class CallSession extends Emitter {
       this.ttsStreamingBuffer.on(TtsStreamingEvents.Pause, this._onTtsStreamingPause.bind(this));
       this.ttsStreamingBuffer.on(TtsStreamingEvents.Resume, this._onTtsStreamingResume.bind(this));
       this.ttsStreamingBuffer.on(TtsStreamingEvents.ConnectFailure, this._onTtsStreamingConnectFailure.bind(this));
+      this.ttsStreamingBuffer.on(TtsStreamingEvents.Connected, this._onTtsStreamingConnected.bind(this));
     }
     else {
       this.logger.info(`CallSession:exec - not a normal call session: ${this.constructor.name}`);
@@ -1305,7 +1348,7 @@ class CallSession extends Emitter {
       }
 
       if (0 === this.tasks.length &&
-        this.requestor instanceof WsRequestor &&
+        this.appIsUsingWebsockets &&
         !this.requestor.closedGracefully &&
         !this.callGone &&
         !this.isConfirmCallSession
@@ -2399,7 +2442,7 @@ Duration=${duration} `
         this.logger.debug(`endpoint was destroyed!! ${this.ep.uuid}`);
       });
 
-      if (this.direction === CallDirection.Inbound) {
+      if (this.direction === CallDirection.Inbound || this.application?.transferredCall) {
         if (task.earlyMedia && !this.req.finalResponseSent) {
           this.res.send(183, {body: ep.local.sdp});
           return {ep};
@@ -2531,7 +2574,7 @@ Duration=${duration} `
     this.backgroundTaskManager.stopAll();
     this.clearOrRestoreActionHookDelayProcessor().catch((err) => {});
 
-    this.ttsStreamingBuffer?.stop();
+    this.stopTtsStream();
 
     this.sttLatencyCalculator?.stop();
   }
@@ -2991,14 +3034,14 @@ Duration=${duration} `
    */
 
   _notifyTaskError(obj) {
-    if (this.requestor instanceof WsRequestor) {
+    if (this.appIsUsingWebsockets) {
       this.requestor.request('jambonz:error', '/error', obj)
         .catch((err) => this.logger.debug({err}, 'CallSession:_notifyTaskError - Error sending'));
     }
   }
 
   _notifyTaskStatus(task, evt) {
-    if (this.notifyEvents && this.requestor instanceof WsRequestor) {
+    if (this.notifyEvents && this.appIsUsingWebsockets) {
       const obj = {...evt, id: task.id, name: task.name};
       this.requestor.request('verb:status', '/status', obj)
         .catch((err) => this.logger.debug({err}, 'CallSession:_notifyTaskStatus - Error sending'));
@@ -3050,7 +3093,7 @@ Duration=${duration} `
   }
 
   _clearTasks(backgroundGather, evt) {
-    if (this.requestor instanceof WsRequestor && !backgroundGather.cleared) {
+    if (this.appIsUsingWebsockets && !backgroundGather.cleared) {
       this.logger.debug({evt}, 'CallSession:_clearTasks on event from background gather');
       try {
         backgroundGather.cleared = true;
@@ -3078,6 +3121,11 @@ Duration=${duration} `
     }
   }
 
+  _onTtsStreamingConnected() {
+    this.requestor?.request('tts:streaming-event', '/streaming-event', {event_type: 'stream_open'})
+      .catch((err) => this.logger.info({err}, 'CallSession:_onTtsStreamingConnected - Error sending'));
+  }
+
   _onTtsStreamingEmpty() {
     const task = this.currentTask;
     if (task && TaskName.Say === task.name) {

lib/session/inbound-call-session.js

@@ -22,6 +22,12 @@ class InboundCallSession extends CallSession {
     this.req = req;
     this.res = res;
 
+    // if the call was canceled before we got here, handle it
+    if (this.req.locals.canceled) {
+      req.locals.logger.info('InboundCallSession: constructor - call was already canceled');
+      this._onCancel();
+    }
+
     req.once('cancel', this._onCancel.bind(this));
 
     this.on('callStatusChange', this._notifyCallStatusChange.bind(this));

lib/tasks/conference.js

@@ -49,7 +49,8 @@ class Conference extends Task {
     this.confName = this.data.name;
     [
       'beep', 'startConferenceOnEnter', 'endConferenceOnExit', 'joinMuted',
-      'maxParticipants', 'waitHook', 'statusHook', 'endHook', 'enterHook', 'endConferenceDuration'
+      'maxParticipants', 'waitHook', 'statusHook', 'endHook', 'enterHook',
+      'endConferenceDuration', 'distributeDtmf'
     ].forEach((attr) => this[attr] = this.data[attr]);
     this.record = this.data.record || {};
     this.statusEvents = [];
@@ -356,6 +357,7 @@ class Conference extends Task {
         //https://developer.signalwire.com/freeswitch/FreeSWITCH-Explained/Modules/mod_conference_3965534/
         // mute |	Enter conference muted
         ...((this.joinMuted || this.speakOnlyTo) && {mute: true}),
+        ...(this.distributeDtmf && {'dist-dtmf': true})
       }});
 
       /**

lib/tasks/config.js

@@ -18,7 +18,8 @@ class TaskConfig extends Task {
       'boostAudioSignal',
       'vad',
       'ttsStream',
-      'autoStreamTts'
+      'autoStreamTts',
+      'disableTtsCache'
     ].forEach((k) => this[k] = this.data[k] || {});
 
     if ('notifyEvents' in this.data) {
@@ -88,6 +89,7 @@ class TaskConfig extends Task {
   get hasReferHook() { return Object.keys(this.data).includes('referHook'); }
   get hasNotifySttLatency() { return Object.keys(this.data).includes('notifySttLatency'); }
   get hasTtsStream() { return Object.keys(this.ttsStream).length; }
+  get hasDisableTtsCache() { return Object.keys(this.data).includes('disableTtsCache'); }
 
   get summary() {
     const phrase = [];
@@ -125,6 +127,7 @@ class TaskConfig extends Task {
       phrase.push(`${this.ttsStream.enable ? 'enable' : 'disable'} ttsStream`);
     }
     if ('autoStreamTts' in this.data) phrase.push(`enable Say.stream value ${this.data.autoStreamTts ? 'on' : 'off'}`);
+    if (this.hasDisableTtsCache) phrase.push(`disableTtsCache ${this.data.disableTtsCache ? 'on' : 'off'}`);
     return `${this.name}{${phrase.join(',')}}`;
   }
 
@@ -357,6 +360,11 @@ class TaskConfig extends Task {
       this.logger.info('Config: disabling ttsStream');
       cs.disableTtsStream();
     }
+
+    if (this.hasDisableTtsCache) {
+      this.logger.info(`set disableTtsCache = ${this.disableTtsCache}`);
+      cs.disableTtsCache = this.data.disableTtsCache;
+    }
   }
 
   async kill(cs) {

lib/tasks/dial.js

@@ -21,7 +21,7 @@ const {parseUri} = require('drachtio-srf');
 const {ANCHOR_MEDIA_ALWAYS,
   JAMBONZ_DIAL_PAI_HEADER,
   JAMBONES_DIAL_SBC_FOR_REGISTERED_USER} = require('../config');
-const { isOnhold, isOpusFirst } = require('../utils/sdp-utils');
+const { isOnhold, isOpusFirst, getLeadingCodec } = require('../utils/sdp-utils');
 const { normalizeJambones } = require('@jambonz/verb-specifications');
 const { selectHostPort } = require('../utils/network');
 const { sleepFor } = require('../utils/helpers');
@@ -158,6 +158,7 @@ class TaskDial extends Task {
 
   get canReleaseMedia() {
     const keepAnchor = this.data.anchorMedia ||
+      this.isTranscoding ||
       this.cs.isBackGroundListen ||
       this.cs.onHoldMusic ||
       ANCHOR_MEDIA_ALWAYS ||
@@ -575,7 +576,7 @@ class TaskDial extends Task {
       proxy: `sip:${sbcAddress}`,
       callingNumber: this.callerId || fromUri.user,
       ...(this.callerName && {callingName: this.callerName}),
-      opusFirst: isOpusFirst(this.cs.ep.remote.sdp),
+      opusFirst: isOpusFirst(this.cs.ep.local.sdp),
       isVideoCall: this.cs.ep.remote.sdp.includes('m=video')
     };
 
@@ -772,6 +773,15 @@ class TaskDial extends Task {
   }
 
   async _connectSingleDial(cs, sd) {
+    // start connect with dialed leg, this is the soonest we can identify transcoding
+    if (this.epOther && sd.ep) {
+      const codecA = getLeadingCodec(this.epOther.local.sdp);
+      const codecB = getLeadingCodec(sd.ep.remote.sdp);
+      this.isTranscoding = (codecA !== codecB);
+      if (this.isTranscoding) {
+        this.logger.info(`Dial:_connectSingleDial - transcoding from ${codecA} (A leg) to ${codecB} (B leg)`);
+      }
+    }
     if (!this.bridged && !this.canReleaseMedia) {
       this.logger.debug('Dial:_connectSingleDial bridging endpoints');
       if (this.epOther) {
@@ -929,7 +939,6 @@ class TaskDial extends Task {
         this.logger.info({err}, 'Dial:_selectSingleDial - Error boosting audio signal');
       }
     }
-
     /* if we can release the media back to the SBC, do so now */
     if (this.canReleaseMedia || this.shouldExitMediaPathEntirely) {
       setTimeout(this._releaseMedia.bind(this, cs, sd, this.shouldExitMediaPathEntirely), 200);

lib/tasks/gather.js

@@ -5,12 +5,14 @@ const {
   AwsTranscriptionEvents,
   AzureTranscriptionEvents,
   DeepgramTranscriptionEvents,
+  GladiaTranscriptionEvents,
   SonioxTranscriptionEvents,
   CobaltTranscriptionEvents,
   IbmTranscriptionEvents,
   NvidiaTranscriptionEvents,
   JambonzTranscriptionEvents,
   AssemblyAiTranscriptionEvents,
+  HoundifyTranscriptionEvents,
   DeepgramfluxTranscriptionEvents,
   VoxistTranscriptionEvents,
   CartesiaTranscriptionEvents,
@@ -93,6 +95,8 @@ class TaskGather extends SttTask {
 
   get needsStt() { return this.input.includes('speech'); }
 
+  get isBackgroundGather() { return this.bugname_prefix === 'background_bargeIn_'; }
+
   get wantsSingleUtterance() {
     return this.data.recognizer?.singleUtterance === true;
   }
@@ -227,7 +231,9 @@ class TaskGather extends SttTask {
 
     const startListening = async(cs, ep) => {
       this._startTimer();
-      if (this.isContinuousAsr && 0 === this.timeout) this._startAsrTimer();
+      if (this.isContinuousAsr && 0 === this.timeout && !this.isBackgroundGather) {
+        this._startAsrTimer();
+      }
       if (this.input.includes('speech') && !this.listenDuringPrompt) {
         try {
           await this._setSpeechHandlers(cs, ep);
@@ -252,7 +258,7 @@ class TaskGather extends SttTask {
             startDtmfListener();
           }
           this._stopVad();
-          if (!this.killed) {
+          if (!this.killed && !this.resolved) {
             startListening(cs, ep);
             if (this.input.includes('speech') && this.vendor === 'nuance' && this.listenDuringPrompt) {
               this.logger.debug('Gather:exec - starting transcription timers after say completes');
@@ -264,19 +270,21 @@ class TaskGather extends SttTask {
         };
         this.sayTask.span = span;
         this.sayTask.ctx = ctx;
-        this.sayTask.exec(cs, {ep})  // kicked off, _not_ waiting for it to complete
+        this.sayTask
+          .exec(cs, {ep})  // kicked off, _not_ waiting for it to complete
+          .then(() => {
+            if (this.sayTask.isStreamingTts) return;
+            this.logger.debug('Gather:exec - nested say task completed');
+            span.end();
+            process();
+            return;
+          })
           .catch((err) => {
             process();
           });
         if (this.sayTask.isStreamingTts && !this.sayTask.closeOnStreamEmpty) {
           // if streaming tts, we do not wait for it to complete if it is not closing the stream automatically
           process();
-        } else {
-          this.sayTask.on('playDone', (err) => {
-            span.end();
-            if (err) this.logger.error({err}, 'Gather:exec Error playing tts');
-            process();
-          });
         }
       }
       else if (this.playTask) {
@@ -288,7 +296,7 @@ class TaskGather extends SttTask {
             startDtmfListener();
           }
           this._stopVad();
-          if (!this.killed) {
+          if (!this.killed && !this.resolved) {
             startListening(cs, ep);
             if (this.input.includes('speech') && this.vendor === 'nuance' && this.listenDuringPrompt) {
               this.logger.debug('Gather:exec - starting transcription timers after play completes');
@@ -300,15 +308,17 @@ class TaskGather extends SttTask {
         };
         this.playTask.span = span;
         this.playTask.ctx = ctx;
-        this.playTask.exec(cs, {ep})  // kicked off, _not_ waiting for it to complete
+        this.playTask
+          .exec(cs, {ep})  // kicked off, _not_ waiting for it to complete
+          .then(() => {
+            this.logger.debug('Gather:exec - nested play task completed');
+            span.end();
+            process();
+            return;
+          })
           .catch((err) => {
             process();
           });
-        this.playTask.on('playDone', (err) => {
-          span.end();
-          if (err) this.logger.error({err}, 'Gather:exec Error playing url');
-          process();
-        });
       }
       else {
         if (this.killed) {
@@ -482,6 +492,16 @@ class TaskGather extends SttTask {
         this.addCustomEventListener(ep, DeepgramfluxTranscriptionEvents.Error, this._onVendorError.bind(this, cs, ep));
         break;
 
+      case 'gladia':
+        this.bugname = `${this.bugname_prefix}gladia_transcribe`;
+        this.addCustomEventListener(
+          ep, GladiaTranscriptionEvents.Transcription, this._onTranscription.bind(this, cs, ep));
+        this.addCustomEventListener(ep, GladiaTranscriptionEvents.Connect, this._onVendorConnect.bind(this, cs, ep));
+        this.addCustomEventListener(ep, GladiaTranscriptionEvents.ConnectFailure,
+          this._onVendorConnectFailure.bind(this, cs, ep));
+        this.addCustomEventListener(ep, GladiaTranscriptionEvents.Error, this._onVendorError.bind(this, cs, ep));
+        break;
+
       case 'soniox':
         this.bugname = `${this.bugname_prefix}soniox_transcribe`;
         this.addCustomEventListener(
@@ -559,6 +579,18 @@ class TaskGather extends SttTask {
           this._onVendorConnectFailure.bind(this, cs, ep));
         break;
 
+      case 'houndify':
+        this.bugname = `${this.bugname_prefix}houndify_transcribe`;
+        this.addCustomEventListener(ep, HoundifyTranscriptionEvents.Transcription,
+          this._onTranscription.bind(this, cs, ep));
+        this.addCustomEventListener(ep, HoundifyTranscriptionEvents.Error,
+          this._onVendorError.bind(this, cs, ep));
+        this.addCustomEventListener(ep, HoundifyTranscriptionEvents.ConnectFailure,
+          this._onVendorConnectFailure.bind(this, cs, ep));
+        this.addCustomEventListener(ep, HoundifyTranscriptionEvents.Connect,
+          this._onVendorConnect.bind(this, cs, ep));
+        break;
+
       case 'voxist':
         this.bugname = `${this.bugname_prefix}voxist_transcribe`;
         this.addCustomEventListener(ep, VoxistTranscriptionEvents.Transcription,
@@ -849,17 +881,15 @@ class TaskGather extends SttTask {
         this._fillerNoiseOn = false;  // in a race, if we just started audio it may sneak through here
         this.ep.api('uuid_break', this.ep.uuid)
           .catch((err) => this.logger.info(err, 'Error killing audio'));
-        cs.clearTtsStream();
+        if (cs.isTtsStreamEnabled) cs.clearTtsStream();
       }
       return;
     }
     if (this.sayTask && !this.sayTask.killed) {
-      this.sayTask.removeAllListeners('playDone');
       this.sayTask.kill(cs);
       this.sayTask = null;
     }
     if (this.playTask && !this.playTask.killed) {
-      this.playTask.removeAllListeners('playDone');
       this.playTask.kill(cs);
       this.playTask = null;
     }
@@ -914,7 +944,7 @@ class TaskGather extends SttTask {
 
     evt = this.normalizeTranscription(evt, this.vendor, 1, this.language,
       this.shortUtterance, this.data.recognizer.punctuation);
-    //this.logger.debug({evt, bugname, finished, vendor: this.vendor}, 'Gather:_onTranscription normalized transcript');
+    this.logger.debug({evt, bugname, finished, vendor: this.vendor}, 'Gather:_onTranscription normalized transcript');
 
     if (evt.alternatives.length === 0) {
       this.logger.info({evt}, 'TaskGather:_onTranscription - got empty transcript, continue listening');
@@ -1080,6 +1110,11 @@ class TaskGather extends SttTask {
         this.cs.requestor.request('verb:hook', this.partialResultHook,  Object.assign({speech: evt},
           this.cs.callInfo, httpHeaders));
       }
+      else if (this.vendor === 'deepgramflux' &&
+        ['EagerEndOfTurn', 'TurnResumed'].includes(evt.vendor.evt?.event)) {
+        this.logger.debug(`Gather:_onTranscription - deepgramflux event detected: ${evt.event}`);
+        this.performAction({speech: evt, reason: 'speechDetected'}, false);
+      }
       if (this.vendor === 'soniox') {
         if (evt.vendor.finalWords.length) {
           this.logger.debug({evt}, 'TaskGather:_onTranscription - buffering soniox transcript');
@@ -1126,7 +1161,7 @@ class TaskGather extends SttTask {
   }
 
   async _startFallback(cs, ep, evt) {
-    if (this.canFallback) {
+    if (this.canFallback()) {
       this._stopTranscribing(ep);
       try {
         this.logger.debug('gather:_startFallback');
@@ -1283,6 +1318,8 @@ class TaskGather extends SttTask {
     }
 
     this.resolved = true;
+    // gather is resolved, prevent any further transcription events while resolve in progress
+    this.removeCustomEventListeners();
     // If bargin is false and ws application return ack to verb:hook
     // the gather should not play any audio
     this._killAudio(this.cs);

lib/tasks/listen.js

@@ -5,6 +5,17 @@ const moment = require('moment');
 const MAX_PLAY_AUDIO_QUEUE_SIZE = 10;
 const DTMF_SPAN_NAME = 'dtmf';
 
+function escapeString(str) {
+  return str
+    .replace(/\\/g, '\\\\')   // Escape backslashes
+    .replace(/"/g, '\\"')     // Escape double quotes
+    .replace(/[\b]/g, '\\b')  // Escape backspace (NOTE: [\b] not \b)
+    .replace(/\f/g, '\\f')    // Escape formfeed
+    .replace(/\n/g, '\\n')    // Escape newlines
+    .replace(/\r/g, '\\r')    // Escape carriage returns
+    .replace(/\t/g, '\\t');   // Escape tabs
+}
+
 class TaskListen extends Task {
   constructor(logger, opts, parentTask) {
     super(logger, opts);
@@ -16,10 +27,21 @@ class TaskListen extends Task {
     this.preconditions = TaskPreconditions.Endpoint;
 
     [
-      'action', 'auth', 'method', 'url', 'finishOnKey', 'maxLength', 'metadata', 'mixType', 'passDtmf', 'playBeep',
+      'action', 'auth', 'method', 'url', 'finishOnKey', 'maxLength', 'mixType', 'passDtmf', 'playBeep',
       'sampleRate', 'timeout', 'transcribe', 'wsAuth', 'disableBidirectionalAudio', 'channel'
     ].forEach((k) => this[k] = this.data[k]);
 
+    //Escape JSON special characters in metadata
+    if (this.data.metadata) {
+      this.metadata = {};
+      for (const key in this.data.metadata) {
+        if (this.data.metadata.hasOwnProperty(key)) {
+          const value = this.data.metadata[key];
+          this.metadata[key] = typeof value === 'string' ? escapeString(value) : value;
+        }
+      }
+    }
+
     this.mixType = this.mixType || 'mono';
     this.sampleRate = this.sampleRate || 8000;
     this.earlyMedia = this.data.earlyMedia === true;

lib/tasks/llm/llms/ultravox_s2s.js

@@ -146,8 +146,9 @@ class TaskLlmUltravox_S2S extends Task {
     return data;
   }
 
-  _unregisterHandlers() {
+  _unregisterHandlers(ep) {
     this.removeCustomEventListeners();
+    ep.removeAllListeners('dtmf');
   }
 
   _registerHandlers(ep) {
@@ -155,6 +156,7 @@ class TaskLlmUltravox_S2S extends Task {
     this.addCustomEventListener(ep, LlmEvents_Ultravox.ConnectFailure, this._onConnectFailure.bind(this, ep));
     this.addCustomEventListener(ep, LlmEvents_Ultravox.Disconnect, this._onDisconnect.bind(this, ep));
     this.addCustomEventListener(ep, LlmEvents_Ultravox.ServerEvent, this._onServerEvent.bind(this, ep));
+    ep.on('dtmf', this._onDtmf.bind(this, ep));
   }
 
   async _startListening(cs, ep) {
@@ -189,7 +191,7 @@ class TaskLlmUltravox_S2S extends Task {
     /* note: the parent llm verb started the span, which is why this is necessary */
     await this.parent.performAction(this.results);
 
-    this._unregisterHandlers();
+    this._unregisterHandlers(ep);
   }
 
   async kill(cs) {
@@ -346,6 +348,18 @@ class TaskLlmUltravox_S2S extends Task {
       excludeEvents: this.excludeEvents
     }, 'TaskLlmUltravox_S2S:_populateEvents');
   }
+
+  _onDtmf(ep, evt) {
+    this.logger.info({evt}, 'TaskLlmUltravox_S2S:_onDtmf - DTMF received');
+    const {dtmf} = evt;
+    const data = {
+      type: 'user_text_message',
+      text: `DTMF received: ${dtmf}`,
+      urgency: 'immediate'
+    };
+    this._api(ep, [ep.uuid, ClientEvent, JSON.stringify(data)])
+      .catch((err) => this.logger.info({err, evt}, 'TaskLlmUltravox_S2S:_onDtmf - Error sending DTMF as text message'));
+  }
 }
 
 module.exports = TaskLlmUltravox_S2S;

lib/tasks/play.js

@@ -6,9 +6,21 @@ class TaskPlay extends Task {
     super(logger, opts);
     this.preconditions = TaskPreconditions.Endpoint;
 
-    this.url = this.data.url.includes('?')
-      ? this.data.url.split('?')[0] + '?' + this.data.url.split('?')[1].replaceAll('.', '%2E')
-      : this.data.url;
+    //Cleanup URLs that contain a querystring with a . unless that querystring is the filename
+    // see https://github.com/jambonz/jambonz-feature-server/pull/1293
+    // and https://github.com/jambonz/jambonz-feature-server/issues/1394 for background
+    if (this.data.url.includes('?')) {
+      if (['.mp3', '.wav'].includes(this.data.url.slice(-4))) {
+        this.url = this.data.url;
+      }
+      else {
+        this.url =  this.data.url.split('?')[0] + '?' + this.data.url.split('?')[1].replaceAll('.', '%2E');
+      }
+    }
+    else {
+      this.url = this.data.url;
+    }
+
     this.seekOffset = this.data.seekOffset || -1;
     this.timeoutSecs = this.data.timeoutSecs || -1;
     this.loop = this.data.loop || 1;

lib/tasks/say.js

@@ -1,9 +1,11 @@
 const assert = require('assert');
 const TtsTask = require('./tts-task');
 const {TaskName, TaskPreconditions} = require('../utils/constants');
+const {JAMBONES_SAY_CHUNK_SIZE} = require('../config');
 const pollySSMLSplit = require('polly-ssml-split');
-const { SpeechCredentialError } = require('../utils/error');
+const { SpeechCredentialError, NonFatalTaskError } = require('../utils/error');
 const { sleepFor } = require('../utils/helpers');
+const { NON_FANTAL_ERRORS } = require('../utils/constants.json');
 
 /**
  * Discard unmatching responses:
@@ -30,7 +32,7 @@ const isMatchingEvent = (logger, filename, playbackId, evt) => {
 const breakLengthyTextIfNeeded = (logger, text) => {
   // As The text can be used for tts streaming, we need to break lengthy text into smaller chunks
 // HIGH_WATER_BUFFER_SIZE defined in tts-streaming-buffer.js
-  const chunkSize = 900;
+  const chunkSize = JAMBONES_SAY_CHUNK_SIZE;
   const isSSML = text.startsWith('<speak>');
   const options = {
     softLimit: 100,
@@ -120,13 +122,11 @@ class TaskSay extends TtsTask {
       }
       if (this.isStreamingTts) await this.handlingStreaming(cs, obj);
       else await this.handling(cs, obj);
-      this.emit('playDone');
     } catch (error) {
       if (error instanceof SpeechCredentialError) {
         // if say failed due to speech credentials, alarm is writtern and error notification is sent
         // finished this say to move to next task.
         this.logger.info({error}, 'Say failed due to SpeechCredentialError, finished!');
-        this.emit('playDone');
         return;
       }
       throw error;
@@ -147,9 +147,6 @@ class TaskSay extends TtsTask {
 
       await cs.startTtsStream();
 
-      cs.requestor?.request('tts:streaming-event', '/streaming-event', {event_type: 'stream_open'})
-        .catch((err) => this.logger.info({err}, 'TaskSay:handlingStreaming - Error sending'));
-
       if (this.text.length !== 0) {
         this.logger.info('TaskSay:handlingStreaming - sending text to TTS stream');
         for (const t of this.text) {
@@ -407,11 +404,19 @@ class TaskSay extends TtsTask {
             this._playResolve = resolve;
             this._playReject = reject;
           });
-          const r = await ep.play(filename);
-          this.logger.debug({r}, 'Say:exec play result');
-          if (r.playbackSeconds == null && r.playbackMilliseconds == null && r.playbackLastOffsetPos == null) {
-            this._playReject(new Error('Playback failed to start'));
+          try {
+            const r = await ep.play(filename);
+            this.logger.debug({r}, 'Say:exec play result');
+            if (r.playbackSeconds == null && r.playbackMilliseconds == null && r.playbackLastOffsetPos == null) {
+              this._playReject(new Error('Playback failed to start'));
+            }
+          } catch (err) {
+            if (NON_FANTAL_ERRORS.includes(err.message)) {
+              throw new NonFatalTaskError(err.message);
+            }
+            throw err;
           }
+
           try {
             // wait for playback-stop event received to confirm if the playback is successful
             await this._playPromise;
@@ -449,8 +454,8 @@ class TaskSay extends TtsTask {
         const {memberId, confName} = cs;
         this.killPlayToConfMember(this.ep, memberId, confName);
       } else if (this.isStreamingTts) {
-        this.logger.debug('TaskSay:kill - clearing TTS stream for streaming audio');
-        cs.clearTtsStream();
+        this.logger.debug('TaskSay:kill - stopping TTS stream for streaming audio');
+        cs.stopTtsStream();
       } else {
         if (!this.notifiedPlayBackStop) {
           this.notifyStatus({event: 'stop-playback'});

lib/tasks/stt-task.js

@@ -171,7 +171,7 @@ class SttTask extends Task {
       try {
         this.sttCredentials = await this._initSpeechCredentials(this.cs, this.vendor, this.label);
       } catch (error) {
-        if (this.canFallback) {
+        if (this.canFallback()) {
           this.notifyError(
             {
               msg: 'ASR error', details:`Invalid vendor ${this.vendor}, Error: ${error}`,
@@ -203,6 +203,56 @@ class SttTask extends Task {
     if (cs.hasGlobalSttPunctuation && !this.data.recognizer.punctuation) {
       this.data.recognizer.punctuation = cs.globalSttPunctuation;
     }
+    if (this.vendor === 'gladia') {
+      const { api_key, region } = this.sttCredentials;
+      const {url} = await this.createGladiaLiveSession({
+        api_key, region,
+        model: this.data.recognizer.model || 'solaria-1',
+        options: this.data.recognizer.gladiaOptions || {}
+      });
+      const {host, pathname, search} = new URL(url);
+      this.sttCredentials.host = host;
+      this.sttCredentials.path = `${pathname}${search}`;
+    }
+  }
+
+
+  async createGladiaLiveSession({
+    api_key,
+    region = 'us-west',
+    model = 'solaria-1',
+    options = {},
+  }) {
+    const url = `https://api.gladia.io/v2/live?region=${region}`;
+    const response = await fetch(url, {
+      method: 'POST',
+      headers: {
+        'x-gladia-key': api_key,
+        'Content-Type': 'application/json'
+      },
+      body: JSON.stringify({
+        encoding: 'wav/pcm',
+        bit_depth: 16,
+        sample_rate: 8000,
+        channels: 1,
+        model,
+        ...options,
+        messages_config: {
+          receive_final_transcripts: true,
+          receive_speech_events: true,
+          receive_errors: true,
+        }
+      })
+    });
+    if (!response.ok) {
+      const error = await response.text();
+      this.logger.error({url, status: response.status, error}, 'Error creating Gladia live session');
+      throw new Error(`Error creating Gladia live session: ${response.status} ${error}`);
+    }
+
+    const data = await response.json();
+    this.logger.debug({url: data.url}, 'Gladia Call registered');
+    return data;
   }
 
   addCustomEventListener(ep, event, handler) {
@@ -210,8 +260,19 @@ class SttTask extends Task {
     ep.addCustomEventListener(event, handler);
   }
 
-  removeCustomEventListeners() {
-    this.eventHandlers.forEach((h) => h.ep.removeCustomEventListener(h.event, h.handler));
+  removeCustomEventListeners(ep) {
+    if (ep) {
+      // for specific endpoint
+      this.eventHandlers.filter((h) => h.ep === ep).forEach((h) => {
+        h.ep.removeCustomEventListener(h.event, h.handler);
+      });
+      this.eventHandlers = this.eventHandlers.filter((h) => h.ep !== ep);
+      return;
+    } else {
+      // for all endpoints
+      this.eventHandlers.forEach((h) => h.ep.removeCustomEventListener(h.event, h.handler));
+      this.eventHandlers = [];
+    }
   }
 
   async _initSpeechCredentials(cs, vendor, label) {
@@ -225,6 +286,7 @@ class SttTask extends Task {
         account_sid: cs.accountSid,
         alert_type: AlertType.STT_NOT_PROVISIONED,
         vendor,
+        label,
         target_sid: cs.callSid
       }).catch((err) => this.logger.info({err}, 'Error generating alert for no stt'));
       // the ASR might have fallback configuration, should not done task here.
@@ -279,11 +341,13 @@ class SttTask extends Task {
     return credentials;
   }
 
-  get canFallback() {
+  canFallback() {
     return this.fallbackVendor && this.isHandledByPrimaryProvider && !this.cs.hasFallbackAsr;
   }
 
-  async _initFallback() {
+  // ep is optional for gather or any verb that have single ep,
+  // but transcribe does need as it might has 2 eps
+  async _initFallback(ep) {
     assert(this.fallbackVendor, 'fallback failed without fallbackVendor configuration');
     this.logger.info(`Failed to use primary STT provider, fallback to ${this.fallbackVendor}`);
     this.isHandledByPrimaryProvider = false;
@@ -296,7 +360,7 @@ class SttTask extends Task {
     this.data.recognizer.label = this.label;
     this.sttCredentials = await this._initSpeechCredentials(this.cs, this.vendor, this.label);
     // cleanup previous listener from previous vendor
-    this.removeCustomEventListeners();
+    this.removeCustomEventListeners(ep);
   }
 
   async compileHintsForCobalt(ep, hostport, model, token, hints) {
@@ -423,6 +487,7 @@ class SttTask extends Task {
       message: 'STT failure reported by vendor',
       detail: evt.error,
       vendor: this.vendor,
+      label: this.label,
       target_sid: cs.callSid
     }).catch((err) => this.logger.info({err}, `Error generating alert for ${this.vendor} connection failure`));
   }
@@ -436,6 +501,7 @@ class SttTask extends Task {
       alert_type: AlertType.STT_FAILURE,
       message: `Failed connecting to ${this.vendor} speech recognizer: ${reason}`,
       vendor: this.vendor,
+      label: this.label,
       target_sid: cs.callSid
     }).catch((err) => this.logger.info({err}, `Error generating alert for ${this.vendor} connection failure`));
   }

lib/tasks/transcribe.js

@@ -6,6 +6,7 @@ const {
   AwsTranscriptionEvents,
   AzureTranscriptionEvents,
   DeepgramTranscriptionEvents,
+  GladiaTranscriptionEvents,
   DeepgramfluxTranscriptionEvents,
   SonioxTranscriptionEvents,
   CobaltTranscriptionEvents,
@@ -14,6 +15,7 @@ const {
   JambonzTranscriptionEvents,
   TranscribeStatus,
   AssemblyAiTranscriptionEvents,
+  HoundifyTranscriptionEvents,
   VoxistTranscriptionEvents,
   CartesiaTranscriptionEvents,
   OpenAITranscriptionEvents,
@@ -68,6 +70,9 @@ class TaskTranscribe extends SttTask {
     this._bufferedTranscripts = [ [], [] ];  // for channel 1 and 2
     this.bugname_prefix = 'transcribe_';
     this.paused = false;
+    // fallback flags
+    this.isHandledByPrimaryProviderForEp1 = true;
+    this.isHandledByPrimaryProviderForEp2 = true;
   }
 
   get name() { return TaskName.Transcribe; }
@@ -254,6 +259,18 @@ class TaskTranscribe extends SttTask {
           this._onVendorConnectFailure.bind(this, cs, ep, channel));
         this.addCustomEventListener(ep, DeepgramfluxTranscriptionEvents.Error, this._onVendorError.bind(this, cs, ep));
 
+        break;
+
+      case 'gladia':
+        this.bugname = `${this.bugname_prefix}gladia_transcribe`;
+        this.addCustomEventListener(ep, GladiaTranscriptionEvents.Transcription,
+          this._onTranscription.bind(this, cs, ep, channel));
+        this.addCustomEventListener(ep, GladiaTranscriptionEvents.Connect,
+          this._onVendorConnect.bind(this, cs, ep));
+        this.addCustomEventListener(ep, GladiaTranscriptionEvents.ConnectFailure,
+          this._onVendorConnectFailure.bind(this, cs, ep, channel));
+        this.addCustomEventListener(ep, GladiaTranscriptionEvents.Error, this._onVendorError.bind(this, cs, ep));
+
         break;
       case 'soniox':
         this.bugname = `${this.bugname_prefix}soniox_transcribe`;
@@ -324,6 +341,18 @@ class TaskTranscribe extends SttTask {
           this._onVendorConnectFailure.bind(this, cs, ep, channel));
         break;
 
+      case 'houndify':
+        this.bugname = `${this.bugname_prefix}houndify_transcribe`;
+        this.addCustomEventListener(ep, HoundifyTranscriptionEvents.Transcription,
+          this._onTranscription.bind(this, cs, ep, channel));
+        this.addCustomEventListener(ep, HoundifyTranscriptionEvents.Error,
+          this._onVendorError.bind(this, cs, ep));
+        this.addCustomEventListener(ep, HoundifyTranscriptionEvents.ConnectFailure,
+          this._onVendorConnectFailure.bind(this, cs, ep, channel));
+        this.addCustomEventListener(ep, HoundifyTranscriptionEvents.Connect,
+          this._onVendorConnect.bind(this, cs, ep));
+        break;
+
       case 'voxist':
         this.bugname = `${this.bugname_prefix}voxist_transcribe`;
         this.addCustomEventListener(ep, VoxistTranscriptionEvents.Transcription,
@@ -750,7 +779,7 @@ class TaskTranscribe extends SttTask {
   }
 
   async _startFallback(cs, _ep, evt) {
-    if (this.canFallback) {
+    if (this.canFallback(_ep)) {
       _ep.stopTranscription({
         vendor: this.vendor,
         bugname: this.bugname,
@@ -760,7 +789,7 @@ class TaskTranscribe extends SttTask {
       try {
         this.notifyError({ msg: 'ASR error',
           details:`STT Vendor ${this.vendor} error: ${evt.error || evt.reason}`, failover: 'in progress'});
-        await this._initFallback();
+        await this._initFallback(_ep);
         let channel = 1;
         if (this.ep !== _ep) {
           channel = 2;
@@ -869,6 +898,41 @@ class TaskTranscribe extends SttTask {
     if (this._asrTimer) clearTimeout(this._asrTimer);
     this._asrTimer = null;
   }
+
+  // We need to keep track the fallback is happened for each endpoint
+  // override the canFallback and _initFallback methods to make sure that
+  // we only fallback once per endpoint
+  // we want to keep track this on task level instead of endpoint level
+  // because the endpoint instance is used across multiple tasks.
+  canFallback(ep) {
+    let isHandledByPrimaryProvider = this.isHandledByPrimaryProvider;
+    if (ep === this.ep) {
+      isHandledByPrimaryProvider = this.isHandledByPrimaryProviderForEp1;
+    } else if (ep === this.ep2) {
+      isHandledByPrimaryProvider = this.isHandledByPrimaryProviderForEp2;
+    }
+
+    const isOneOfEndpointAlreadyFallenBack = !!this.ep && !!this.ep2 &&
+      this.isHandledByPrimaryProviderForEp1 !== this.isHandledByPrimaryProviderForEp2;
+
+    // fallback is configured
+    return this.fallbackVendor &&
+      // has this endpoint already fallen back
+      isHandledByPrimaryProvider &&
+      // in global level, is there any fallback is already happened
+      // one fallen endpoint will mark cs.hasFallbackAsr to true,
+      // so if one endpoint was fallen, the other endpoint would be able to fallback.
+      (isOneOfEndpointAlreadyFallenBack || !this.cs.hasFallbackAsr);
+  }
+
+  _initFallback(ep) {
+    if (ep === this.ep) {
+      this.isHandledByPrimaryProviderForEp1 = false;
+    } else if (ep === this.ep2) {
+      this.isHandledByPrimaryProviderForEp2 = false;
+    }
+    return super._initFallback(ep);
+  }
 }
 
 module.exports = TaskTranscribe;

lib/tasks/tts-task.js

@@ -41,6 +41,10 @@ class TtsTask extends Task {
 
   async exec(cs) {
     super.exec(cs);
+    // update disableTtsCache from call session if not set in task
+    if (this.data.disableTtsCache == null) {
+      this.disableTtsCache = cs.disableTtsCache;
+    }
     if (cs.synthesizer) {
       this.options = {...cs.synthesizer.options, ...this.options};
       this.data.synthesizer = this.data.synthesizer || {};
@@ -81,54 +85,67 @@ class TtsTask extends Task {
   }
 
   async setTtsStreamingChannelVars(vendor, language, voice, credentials, ep) {
-    const {api_key, model_id, custom_tts_streaming_url, auth_token} = credentials;
-    let obj;
+    const {api_key, model_id, api_uri, custom_tts_streaming_url, auth_token, options} = credentials;
+    // api_key, model_id, api_uri, custom_tts_streaming_url, and auth_token are encoded in the credentials
+    // allow them to be overriden via config, using options
+    // give preference to options passed in via config
+    const parsed_options = options ? JSON.parse(options) : {};
+    const local_options = {...parsed_options, ...this.options};
+    const local_voice_settings = {...(parsed_options.voice_settings || {}), ...(this.options.voice_settings || {})};
+    const local_api_key =  local_options.api_key ?? api_key;
+    const local_model_id = local_options.model_id ?? model_id;
+    const local_api_uri = local_options.api_uri ?? api_uri;
+    const local_custom_tts_streaming_url = local_options.custom_tts_streaming_url ?? custom_tts_streaming_url;
+    const local_auth_token = local_options.auth_token ?? auth_token;
 
-    this.logger.debug(`setTtsStreamingChannelVars: vendor: ${vendor}, language: ${language}, voice: ${voice}`);
+
+    let obj;
 
     switch (vendor) {
       case 'deepgram':
         obj = {
-          DEEPGRAM_API_KEY: api_key,
+          DEEPGRAM_API_KEY: local_api_key,
           DEEPGRAM_TTS_STREAMING_MODEL: voice
         };
         break;
       case 'cartesia':
         obj = {
-          CARTESIA_API_KEY: api_key,
-          CARTESIA_TTS_STREAMING_MODEL_ID: model_id,
+          CARTESIA_API_KEY: local_api_key,
+          CARTESIA_TTS_STREAMING_MODEL_ID: local_model_id,
           CARTESIA_TTS_STREAMING_VOICE_ID: voice,
           CARTESIA_TTS_STREAMING_LANGUAGE: language || 'en',
         };
         break;
       case 'elevenlabs':
-        const {stability, similarity_boost, use_speaker_boost, style, speed} = this.options.voice_settings || {};
+        // eslint-disable-next-line max-len
+        const {stability, similarity_boost, use_speaker_boost, style, speed} = local_voice_settings || {};
         obj = {
-          ELEVENLABS_API_KEY: api_key,
-          ELEVENLABS_TTS_STREAMING_MODEL_ID: model_id,
+          ELEVENLABS_API_KEY: local_api_key,
+          ...(api_uri && {ELEVENLABS_API_URI: local_api_uri}),
+          ELEVENLABS_TTS_STREAMING_MODEL_ID: local_model_id,
           ELEVENLABS_TTS_STREAMING_VOICE_ID: voice,
           // 20/12/2024 - only eleven_turbo_v2_5 support multiple language
-          ...(['eleven_turbo_v2_5'].includes(model_id) && {ELEVENLABS_TTS_STREAMING_LANGUAGE: language}),
+          ...(['eleven_turbo_v2_5'].includes(local_model_id) && {ELEVENLABS_TTS_STREAMING_LANGUAGE: language}),
           ...(stability && {ELEVENLABS_TTS_STREAMING_VOICE_SETTINGS_STABILITY: stability}),
           ...(similarity_boost && {ELEVENLABS_TTS_STREAMING_VOICE_SETTINGS_SIMILARITY_BOOST: similarity_boost}),
           ...(use_speaker_boost && {ELEVENLABS_TTS_STREAMING_VOICE_SETTINGS_USE_SPEAKER_BOOST: use_speaker_boost}),
           ...(style && {ELEVENLABS_TTS_STREAMING_VOICE_SETTINGS_STYLE: style}),
           // speed has value 0.7 to 1.2, 1.0 is default, make sure we send the value event it's 0
           ...(speed !== null && speed !== undefined && {ELEVENLABS_TTS_STREAMING_VOICE_SETTINGS_SPEED: `${speed}`}),
-          ...(this.options.pronunciation_dictionary_locators &&
-            Array.isArray(this.options.pronunciation_dictionary_locators) && {
+          ...(local_options.pronunciation_dictionary_locators &&
+            Array.isArray(local_options.pronunciation_dictionary_locators) && {
             ELEVENLABS_TTS_STREAMING_PRONUNCIATION_DICTIONARY_LOCATORS:
-            JSON.stringify(this.options.pronunciation_dictionary_locators)
+            JSON.stringify(local_options.pronunciation_dictionary_locators)
           }),
         };
         break;
       case 'rimelabs':
         const {
           pauseBetweenBrackets, phonemizeBetweenBrackets, inlineSpeedAlpha, speedAlpha, reduceLatency
-        } = this.options;
+        } = local_options;
         obj = {
-          RIMELABS_API_KEY: api_key,
-          RIMELABS_TTS_STREAMING_MODEL_ID: model_id,
+          RIMELABS_API_KEY: local_api_key,
+          RIMELABS_TTS_STREAMING_MODEL_ID: local_model_id,
           RIMELABS_TTS_STREAMING_VOICE_ID: voice,
           RIMELABS_TTS_STREAMING_LANGUAGE: language || 'en',
           ...(pauseBetweenBrackets && {RIMELABS_TTS_STREAMING_PAUSE_BETWEEN_BRACKETS: pauseBetweenBrackets}),
@@ -143,8 +160,8 @@ class TtsTask extends Task {
         if (vendor.startsWith('custom:')) {
           const use_tls = custom_tts_streaming_url.startsWith('wss://');
           obj = {
-            CUSTOM_TTS_STREAMING_HOST: custom_tts_streaming_url.replace(/^(ws|wss):\/\//, ''),
-            CUSTOM_TTS_STREAMING_API_KEY: auth_token,
+            CUSTOM_TTS_STREAMING_HOST: local_custom_tts_streaming_url.replace(/^(ws|wss):\/\//, ''),
+            CUSTOM_TTS_STREAMING_API_KEY: local_auth_token,
             CUSTOM_TTS_STREAMING_VOICE_ID: voice,
             CUSTOM_TTS_STREAMING_LANGUAGE: language || 'en',
             CUSTOM_TTS_STREAMING_USE_TLS: use_tls
@@ -257,15 +274,16 @@ class TtsTask extends Task {
           account_sid,
           alert_type: AlertType.TTS_NOT_PROVISIONED,
           vendor,
+          label,
           target_sid: cs.callSid
         }).catch((err) => this.logger.info({err}, 'Error generating alert for no tts'));
         throw new SpeechCredentialError('no provisioned speech credentials for TTS');
       }
 
       /* produce an audio segment from the provided text */
-      const generateAudio = async(text) => {
-        if (this.killed) return;
-        if (text.startsWith('silence_stream://')) return text;
+      const generateAudio = async(text, index) => {
+        if (this.killed) return {index, filePath: null};
+        if (text.startsWith('silence_stream://')) return {index, filePath: text};
 
         /* otel: trace time for tts */
         if (!preCache && !this._disableTracing)  {
@@ -294,7 +312,6 @@ class TtsTask extends Task {
             renderForCaching: preCache
           });
           if (!filePath.startsWith('say:')) {
-            this.playbackIds.push(null);
             this.logger.debug(`Say: file ${filePath}, served from cache ${servedFromCache}`);
             if (filePath) cs.trackTmpFile(filePath);
             if (this.otelSpan) {
@@ -322,10 +339,11 @@ class TtsTask extends Task {
                 'id': this.id
               });
             }
+            return {index, filePath, playbackId: null};
           }
           else {
-            this.playbackIds.push(extractPlaybackId(filePath));
-            this.logger.debug({playbackIds: this.playbackIds}, 'Say: a streaming tts api will be used');
+            const playbackId = extractPlaybackId(filePath);
+            this.logger.debug('Say: a streaming tts api will be used');
             const modifiedPath = filePath.replace('say:{', `say:{session-uuid=${ep.uuid},`);
             this.notifyStatus({
               event: 'synthesized-audio',
@@ -334,9 +352,8 @@ class TtsTask extends Task {
               servedFromCache,
               'id': this.id
             });
-            return modifiedPath;
+            return {index, filePath: modifiedPath, playbackId};
           }
-          return filePath;
         } catch (err) {
           this.logger.info({err}, 'Error synthesizing tts');
           if (this.otelSpan) this.otelSpan.end();
@@ -344,6 +361,7 @@ class TtsTask extends Task {
             account_sid: cs.accountSid,
             alert_type: AlertType.TTS_FAILURE,
             vendor,
+            label,
             detail: err.message,
             target_sid: cs.callSid
           }).catch((err) => this.logger.info({err}, 'Error generating alert for tts failure'));
@@ -351,8 +369,20 @@ class TtsTask extends Task {
         }
       };
 
-      const arr = this.text.map((t) => (this._validateURL(t) ? t : generateAudio(t)));
-      return (await Promise.all(arr)).filter((fp) => fp && fp.length);
+      // process all text segments in parallel will cause ordering issue
+      // so we attach index to each promise result and sort them later
+
+      const arr = this.text.map((t, index) => (this._validateURL(t) ?
+        Promise.resolve({index, filePath: t, playbackId: null}) : generateAudio(t, index)));
+      const results = await Promise.all(arr);
+      const sorted = results.sort((a, b) => a.index - b.index);
+
+      return sorted
+        .filter((fp) => fp.filePath && fp.filePath.length)
+        .map((r) => {
+          this.playbackIds.push(r.playbackId);
+          return r.filePath;
+        });
     } catch (err) {
       this.logger.info(err, 'TaskSay:exec error');
       throw err;

lib/utils/amd-utils.js

@@ -405,19 +405,21 @@ module.exports = (logger) => {
     if (ep.amd) {
       vendor = ep.amd.vendor;
       ep.amd.stopAllTimers();
-
-      ep.removeListener(GoogleTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
-      ep.removeListener(GoogleTranscriptionEvents.EndOfUtterance, ep.amd.EndOfUtteranceHandler);
-      ep.removeListener(AwsTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
-      ep.removeListener(AzureTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
-      ep.removeListener(AzureTranscriptionEvents.NoSpeechDetected, ep.amd.noSpeechHandler);
-      ep.removeListener(NuanceTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
-      ep.removeListener(DeepgramTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
-      ep.removeListener(SonioxTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
-      ep.removeListener(IbmTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
-      ep.removeListener(NvidiaTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
-      ep.removeListener(JambonzTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
-
+      try {
+        ep.removeListener(GoogleTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
+        ep.removeListener(GoogleTranscriptionEvents.EndOfUtterance, ep.amd.EndOfUtteranceHandler);
+        ep.removeListener(AwsTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
+        ep.removeListener(AzureTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
+        ep.removeListener(AzureTranscriptionEvents.NoSpeechDetected, ep.amd.noSpeechHandler);
+        ep.removeListener(NuanceTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
+        ep.removeListener(DeepgramTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
+        ep.removeListener(SonioxTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
+        ep.removeListener(IbmTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
+        ep.removeListener(NvidiaTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
+        ep.removeListener(JambonzTranscriptionEvents.Transcription, ep.amd.transcriptionHandler);
+      } catch (error) {
+        logger.error('Unable to Remove AMD Listener', error);
+      }
       ep.amd = null;
     }
 

lib/utils/constants.json

@@ -103,6 +103,12 @@
     "Connect": "deepgramflux_transcribe::connect",
     "Error": "deepgramflux_transcribe::error"
   },
+  "GladiaTranscriptionEvents": {
+    "Transcription": "gladia_transcribe::transcription",
+    "ConnectFailure": "gladia_transcribe::connect_failed",
+    "Connect": "gladia_transcribe::connect",
+    "Error": "gladia_transcribe::error"
+  },
   "SonioxTranscriptionEvents": {
     "Transcription": "soniox_transcribe::transcription",
     "Error": "soniox_transcribe::error"
@@ -169,6 +175,12 @@
     "ConnectFailure": "assemblyai_transcribe::connect_failed",
     "Connect": "assemblyai_transcribe::connect"
   },
+  "HoundifyTranscriptionEvents": {
+    "Transcription": "houndify_transcribe::transcription",
+    "Error": "houndify_transcribe::error",
+    "ConnectFailure": "houndify_transcribe::connect_failed",
+    "Connect": "houndify_transcribe::connect"
+  },
   "VoxistTranscriptionEvents": {
     "Transcription": "voxist_transcribe::transcription",
     "Error": "voxist_transcribe::error",
@@ -323,7 +335,8 @@
     "Empty": "tts_streaming::empty",
     "Pause": "tts_streaming::pause",
     "Resume": "tts_streaming::resume",
-    "ConnectFailure": "tts_streaming::connect_failed"
+    "ConnectFailure": "tts_streaming::connect_failed",
+    "Connected": "tts_streaming::connected"
   },
   "TtsStreamingConnectionStatus": {
     "NotConnected": "not_connected",
@@ -343,5 +356,8 @@
   "WS_CLOSE_CODES": {
     "NormalClosure": 1000,
     "GoingAway": 1001
-  }
+  },
+  "NON_FANTAL_ERRORS": [
+    "File Not Found"
+  ]
 }

lib/utils/db-utils.js

@@ -81,6 +81,11 @@ const speechMapper = (cred) => {
       obj.deepgram_tts_uri = o.deepgram_tts_uri;
       obj.deepgram_stt_use_tls = o.deepgram_stt_use_tls;
     }
+    else if ('gladia' === obj.vendor) {
+      const o = JSON.parse(decrypt(credential));
+      obj.api_key = o.api_key;
+      obj.region = o.region;
+    }
     else if ('deepgramflux' === obj.vendor) {
       const o = JSON.parse(decrypt(credential));
       obj.api_key = o.api_key;
@@ -101,6 +106,7 @@ const speechMapper = (cred) => {
       const o = JSON.parse(decrypt(credential));
       obj.api_key = o.api_key;
       obj.model_id = o.model_id;
+      obj.api_uri = o.api_uri;
       obj.options = o.options;
     }
     else if ('playht' === obj.vendor) {
@@ -141,6 +147,13 @@ const speechMapper = (cred) => {
       obj.api_key = o.api_key;
       obj.service_version = o.service_version;
     }
+    else if ('houndify' === obj.vendor) {
+      const o = JSON.parse(decrypt(credential));
+      obj.client_id = o.client_id;
+      obj.client_key = o.client_key;
+      obj.user_id = o.user_id;
+      obj.houndify_server_uri = o.houndify_server_uri;
+    }
     else if ('voxist' === obj.vendor) {
       const o = JSON.parse(decrypt(credential));
       obj.api_key = o.api_key;

lib/utils/http-requestor.js

@@ -191,7 +191,7 @@ class HttpRequestor extends BaseRequestor {
         method,
         headers: hdrs,
         ...('POST' === method && {body: JSON.stringify(payload)}),
-        timeout: HTTP_TIMEOUT,
+        headersTimeout: HTTP_TIMEOUT,
         followRedirects: false
       };
 

lib/utils/sbc-pinger.js

@@ -100,6 +100,39 @@ module.exports = (logger) => {
   else if (K8S) {
     lifecycleEmitter.scaleIn = () => process.exit(0);
   }
+  else {
+    process.on('SIGUSR1', () => {
+      logger.info('received SIGUSR1: begin drying up calls for scale-in');
+      dryUpCalls = true;
+
+      const {srf} = require('../..');
+      const {writeSystemAlerts} = srf.locals;
+      if (writeSystemAlerts) {
+        const {SystemState, FEATURE_SERVER} = require('./constants');
+        writeSystemAlerts({
+          system_component: FEATURE_SERVER,
+          state : SystemState.GracefulShutdownInProgress,
+          fields : {
+            detail: `feature-server with process_id ${process.pid} shutdown in progress`,
+            host: srf.locals?.ipv4
+          }
+        });
+      }
+      pingProxies(srf);
+
+      // if we have zero calls, we can complete the scale-in right
+      setTimeout(() => {
+        const calls = srf.locals.sessionTracker.count;
+        if (calls === 0) {
+          logger.info('scale-in can complete immediately as we have no calls in progress');
+          process.exit(0);
+        }
+        else {
+          logger.info(`${calls} calls in progress; scale-in will complete when they are done`);
+        }
+      }, 5000);
+    });
+  }
 
 
   async function pingProxies(srf) {

lib/utils/sdp-utils.js

@@ -55,11 +55,28 @@ const extractSdpMedia = (sdp) => {
   }
 };
 
+const getLeadingCodec = (sdp) => {
+  if (!sdp) {
+    return null;
+  }
+
+  const parsed = sdpTransform.parse(sdp);
+  const audio = parsed.media?.find((m) => m.type === 'audio');
+
+  if (!audio) {
+    return null;
+  }
+
+  return audio.rtp?.[0]?.codec || null;
+};
+
+
 module.exports = {
   isOnhold,
   mergeSdpMedia,
   extractSdpMedia,
   isOpusFirst,
   makeOpusFirst,
-  removeVideoSdp
+  removeVideoSdp,
+  getLeadingCodec
 };

lib/utils/stt-latency-calculator.js

@@ -127,7 +127,6 @@ class SttLatencyCalculator extends Emitter {
 
   calculateLatency() {
     if (!this.isRunning) {
-      this.logger.debug('Latency calculator is not running, cannot calculate latency, returning default values');
       return null;
     }
 

lib/utils/transcription-utils.js

@@ -131,6 +131,43 @@ const stickyVars = {
     'OPENAI_TURN_DETECTION_PREFIX_PADDING_MS',
     'OPENAI_TURN_DETECTION_SILENCE_DURATION_MS',
   ],
+  houndify: [
+    'HOUNDIFY_CLIENT_ID',
+    'HOUNDIFY_CLIENT_KEY',
+    'HOUNDIFY_USER_ID',
+    'HOUNDIFY_MAX_SILENCE_SECONDS',
+    'HOUNDIFY_MAX_SILENCE_AFTER_FULL_QUERY_SECONDS',
+    'HOUNDIFY_MAX_SILENCE_AFTER_PARTIAL_QUERY_SECONDS',
+    'HOUNDIFY_VAD_SENSITIVITY',
+    'HOUNDIFY_VAD_TIMEOUT',
+    'HOUNDIFY_VAD_MODE',
+    'HOUNDIFY_VAD_VOICE_MS',
+    'HOUNDIFY_VAD_SILENCE_MS',
+    'HOUNDIFY_VAD_DEBUG',
+    'HOUNDIFY_AUDIO_FORMAT',
+    'HOUNDIFY_ENABLE_NOISE_REDUCTION',
+    'HOUNDIFY_AUDIO_ENDPOINT',
+    'HOUNDIFY_ENABLE_PROFANITY_FILTER',
+    'HOUNDIFY_ENABLE_PUNCTUATION',
+    'HOUNDIFY_ENABLE_CAPITALIZATION',
+    'HOUNDIFY_CONFIDENCE_THRESHOLD',
+    'HOUNDIFY_ENABLE_DISFLUENCY_FILTER',
+    'HOUNDIFY_MAX_RESULTS',
+    'HOUNDIFY_ENABLE_WORD_TIMESTAMPS',
+    'HOUNDIFY_MAX_ALTERNATIVES',
+    'HOUNDIFY_PARTIAL_TRANSCRIPT_INTERVAL',
+    'HOUNDIFY_SESSION_TIMEOUT',
+    'HOUNDIFY_CONNECTION_TIMEOUT',
+    'HOUNDIFY_LATITUDE',
+    'HOUNDIFY_LONGITUDE',
+    'HOUNDIFY_CITY',
+    'HOUNDIFY_STATE',
+    'HOUNDIFY_COUNTRY',
+    'HOUNDIFY_TIMEZONE',
+    'HOUNDIFY_DOMAIN',
+    'HOUNDIFY_CUSTOM_VOCABULARY',
+    'HOUNDIFY_LANGUAGE_MODEL'
+  ],
 };
 
 /**
@@ -339,6 +376,30 @@ const normalizeDeepgram = (evt, channel, language, shortUtterance) => {
   };
 };
 
+const normalizeGladia = (evt, channel, language, shortUtterance) => {
+  const copy = JSON.parse(JSON.stringify(evt));
+
+  // Handle Gladia transcript format
+  if (evt.type === 'transcript' && evt.data && evt.data.utterance) {
+    const utterance = evt.data.utterance;
+    const alternatives = [{
+      confidence: utterance.confidence || 0,
+      transcript: utterance.text || '',
+    }];
+
+    return {
+      language_code: utterance.language || language,
+      channel_tag: channel,
+      is_final: evt.data.is_final || false,
+      alternatives,
+      vendor: {
+        name: 'gladia',
+        evt: copy
+      }
+    };
+  }
+};
+
 const normalizeDeepgramFlux = (evt, channel, language) => {
   const copy = JSON.parse(JSON.stringify(evt));
 
@@ -582,6 +643,30 @@ const normalizeAssemblyAi = (evt, channel, language) => {
   };
 };
 
+const normalizeHoundify = (evt, channel, language) => {
+  const copy = JSON.parse(JSON.stringify(evt));
+  const alternatives = [];
+  const is_final = evt.ResultsAreFinal && evt.ResultsAreFinal[0] === true;
+  if (evt.Disambiguation && evt.Disambiguation.ChoiceData && evt.Disambiguation.ChoiceData.length > 0) {
+    // Handle Houndify Voice Search Result format
+    const choiceData = evt.Disambiguation.ChoiceData[0];
+    alternatives.push({
+      confidence: choiceData.ConfidenceScore || choiceData.ASRConfidence || 0.0,
+      transcript: choiceData.FormattedTranscription || choiceData.Transcription || '',
+    });
+  }
+  return {
+    language_code: language,
+    channel_tag: channel,
+    is_final,
+    alternatives,
+    vendor: {
+      name: 'houndify',
+      evt: copy
+    }
+  };
+};
+
 const normalizeVoxist = (evt, channel, language) => {
   const copy = JSON.parse(JSON.stringify(evt));
   return {
@@ -681,6 +766,8 @@ module.exports = (logger) => {
     switch (vendor) {
       case 'deepgram':
         return normalizeDeepgram(evt, channel, language, shortUtterance);
+      case 'gladia':
+        return normalizeGladia(evt, channel, language, shortUtterance);
       case 'deepgramflux':
         return normalizeDeepgramFlux(evt, channel, language, shortUtterance);
       case 'microsoft':
@@ -701,6 +788,8 @@ module.exports = (logger) => {
         return normalizeCobalt(evt, channel, language);
       case 'assemblyai':
         return normalizeAssemblyAi(evt, channel, language, shortUtterance);
+      case 'houndify':
+        return normalizeHoundify(evt, channel, language, shortUtterance);
       case 'voxist':
         return normalizeVoxist(evt, channel, language);
       case 'cartesia':
@@ -831,7 +920,7 @@ module.exports = (logger) => {
         ...(rOpts.initialSpeechTimeoutMs > 0 &&
           {AZURE_INITIAL_SPEECH_TIMEOUT_MS: rOpts.initialSpeechTimeoutMs}),
         ...(rOpts.requestSnr && {AZURE_REQUEST_SNR: 1}),
-        ...(rOpts.audioLogging && {AZURE_AUDIO_LOGGING: 1}),
+        ...(azureOptions.audioLogging && {AZURE_AUDIO_LOGGING: 1}),
         ...{AZURE_USE_OUTPUT_FORMAT_DETAILED: 1},
         ...(azureOptions.speechSegmentationSilenceTimeoutMs &&
           {AZURE_SPEECH_SEGMENTATION_SILENCE_TIMEOUT_MS: azureOptions.speechSegmentationSilenceTimeoutMs}),
@@ -996,6 +1085,13 @@ module.exports = (logger) => {
         ...(keyterms && keyterms.length > 0 && {DEEPGRAMFLUX_SPEECH_KEYTERMS: keyterms.join(',')}),
       };
     }
+    else if ('gladia' === vendor) {
+      const {host, path} = sttCredentials;
+      opts = {
+        GLADIA_SPEECH_HOST: host,
+        GLADIA_SPEECH_PATH: path,
+      };
+    }
     else if ('soniox' === vendor) {
       const {sonioxOptions = {}} = rOpts;
       const {storage = {}} = sonioxOptions;
@@ -1122,6 +1218,61 @@ module.exports = (logger) => {
           {ASSEMBLYAI_WORD_BOOST: JSON.stringify(rOpts.hints)})
       };
     }
+    else if ('houndify' === vendor) {
+      const {
+        latitude, longitude, city, state, country, timeZone, domain, audioEndpoint,
+        maxSilenceSeconds, maxSilenceAfterFullQuerySeconds, maxSilenceAfterPartialQuerySeconds,
+        vadSensitivity, vadTimeout, vadMode, vadVoiceMs, vadSilenceMs, vadDebug,
+        audioFormat, enableNoiseReduction, enableProfanityFilter, enablePunctuation,
+        enableCapitalization, confidenceThreshold, enableDisfluencyFilter,
+        maxResults, enableWordTimestamps, maxAlternatives, partialTranscriptInterval,
+        sessionTimeout, connectionTimeout, customVocabulary, languageModel,
+        requestInfo, sampleRate
+      } = rOpts.houndifyOptions || {};
+      const audioEndpointUri = audioEndpoint || sttCredentials.houndify_server_uri;
+
+      opts = {
+        ...opts,
+        HOUNDIFY_CLIENT_ID: sttCredentials.client_id,
+        HOUNDIFY_CLIENT_KEY: sttCredentials.client_key,
+        HOUNDIFY_USER_ID: sttCredentials.user_id,
+        HOUNDIFY_MAX_SILENCE_SECONDS: maxSilenceSeconds || 5,
+        HOUNDIFY_MAX_SILENCE_AFTER_FULL_QUERY_SECONDS: maxSilenceAfterFullQuerySeconds || 1,
+        HOUNDIFY_MAX_SILENCE_AFTER_PARTIAL_QUERY_SECONDS: maxSilenceAfterPartialQuerySeconds || 1.5,
+        ...(vadSensitivity && {HOUNDIFY_VAD_SENSITIVITY: vadSensitivity}),
+        ...(vadTimeout && {HOUNDIFY_VAD_TIMEOUT: vadTimeout}),
+        ...(vadMode && {HOUNDIFY_VAD_MODE: vadMode}),
+        ...(vadVoiceMs && {HOUNDIFY_VAD_VOICE_MS: vadVoiceMs}),
+        ...(vadSilenceMs && {HOUNDIFY_VAD_SILENCE_MS: vadSilenceMs}),
+        ...(vadDebug && {HOUNDIFY_VAD_DEBUG: vadDebug}),
+        ...(audioFormat && {HOUNDIFY_AUDIO_FORMAT: audioFormat}),
+        ...(enableNoiseReduction && {HOUNDIFY_ENABLE_NOISE_REDUCTION: enableNoiseReduction}),
+        ...(enableProfanityFilter && {HOUNDIFY_ENABLE_PROFANITY_FILTER: enableProfanityFilter}),
+        ...(enablePunctuation && {HOUNDIFY_ENABLE_PUNCTUATION: enablePunctuation}),
+        ...(enableCapitalization && {HOUNDIFY_ENABLE_CAPITALIZATION: enableCapitalization}),
+        ...(confidenceThreshold && {HOUNDIFY_CONFIDENCE_THRESHOLD: confidenceThreshold}),
+        ...(enableDisfluencyFilter && {HOUNDIFY_ENABLE_DISFLUENCY_FILTER: enableDisfluencyFilter}),
+        ...(maxResults && {HOUNDIFY_MAX_RESULTS: maxResults}),
+        ...(enableWordTimestamps && {HOUNDIFY_ENABLE_WORD_TIMESTAMPS: enableWordTimestamps}),
+        ...(maxAlternatives && {HOUNDIFY_MAX_ALTERNATIVES: maxAlternatives}),
+        ...(partialTranscriptInterval && {HOUNDIFY_PARTIAL_TRANSCRIPT_INTERVAL: partialTranscriptInterval}),
+        ...(sessionTimeout && {HOUNDIFY_SESSION_TIMEOUT: sessionTimeout}),
+        ...(connectionTimeout && {HOUNDIFY_CONNECTION_TIMEOUT: connectionTimeout}),
+        ...(latitude && {HOUNDIFY_LATITUDE: latitude}),
+        ...(longitude && {HOUNDIFY_LONGITUDE: longitude}),
+        ...(city && {HOUNDIFY_CITY: city}),
+        ...(state && {HOUNDIFY_STATE: state}),
+        ...(country && {HOUNDIFY_COUNTRY: country}),
+        ...(timeZone && {HOUNDIFY_TIMEZONE: timeZone}),
+        ...(domain && {HOUNDIFY_DOMAIN: domain}),
+        ...(audioEndpointUri && {HOUNDIFY_AUDIO_ENDPOINT: audioEndpointUri}),
+        ...(customVocabulary && {HOUNDIFY_CUSTOM_VOCABULARY:
+          Array.isArray(customVocabulary) ? customVocabulary.join(',') : customVocabulary}),
+        ...(languageModel && {HOUNDIFY_LANGUAGE_MODEL: languageModel}),
+        ...(requestInfo && {HOUNDIFY_REQUEST_INFO: JSON.stringify(requestInfo)}),
+        ...(sampleRate && {HOUNDIFY_SAMPLING_RATE: sampleRate}),
+      };
+    }
     else if ('voxist' === vendor) {
       opts = {
         ...opts,

lib/utils/tts-streaming-buffer.js

@@ -80,7 +80,7 @@ class TtsStreamingBuffer extends Emitter {
     clearTimeout(this.timer);
     this.removeCustomEventListeners();
     if (this.ep) {
-      this._api(this.ep, [this.ep.uuid, 'close'])
+      this._api(this.ep, [this.ep.uuid, 'stop'])
         .catch((err) =>
           this.logger.info({ err }, 'TtsStreamingBuffer:stop Error closing TTS streaming')
         );
@@ -163,7 +163,6 @@ class TtsStreamingBuffer extends Emitter {
   }
 
   clear() {
-    this.logger.debug('TtsStreamingBuffer:clear');
     if (this._connectionStatus !== TtsStreamingConnectionStatus.Connected) return;
     clearTimeout(this.timer);
     this._api(this.ep, [this.ep.uuid, 'clear']).catch((err) =>
@@ -193,10 +192,7 @@ class TtsStreamingBuffer extends Emitter {
         this.logger.debug('TtsStreamingBuffer:_feedQueue TTS stream is not open or no endpoint available');
         return;
       }
-      if (
-        this._connectionStatus === TtsStreamingConnectionStatus.NotConnected ||
-        this._connectionStatus === TtsStreamingConnectionStatus.Failed
-      ) {
+      if (this._connectionStatus !== TtsStreamingConnectionStatus.Connected) {
         this.logger.debug('TtsStreamingBuffer:_feedQueue TTS stream is not connected');
         return;
       }
@@ -224,7 +220,8 @@ class TtsStreamingBuffer extends Emitter {
           this.queue.shift();
         }
         // Immediately send all accumulated text (ignoring sentence boundaries).
-        if (flushText.length > 0) {
+        // Skip sending if flushText is only whitespace.
+        if (flushText.length > 0 && !isWhitespace(flushText)) {
           const modifiedFlushText = flushText.replace(/\n\n/g, '\n \n');
           try {
             await this._api(this.ep, [this.ep.uuid, 'send', modifiedFlushText]);
@@ -278,6 +275,14 @@ class TtsStreamingBuffer extends Emitter {
       }
       const chunk = combinedText.slice(0, chunkEnd);
 
+      // Check if the chunk is only whitespace before processing the queue
+      // If so, wait for more meaningful text
+      if (isWhitespace(chunk)) {
+        this.logger.debug('TtsStreamingBuffer:_feedQueue chunk is only whitespace, waiting for more text');
+        this._setTimerIfNeeded();
+        return;
+      }
+
       // Now we iterate over the queue items
       // and deduct their lengths until we've accounted for chunkEnd characters.
       let remaining = chunkEnd;
@@ -301,6 +306,14 @@ class TtsStreamingBuffer extends Emitter {
       this.bufferedLength -= chunkEnd;
 
       const modifiedChunk = chunk.replace(/\n\n/g, '\n \n');
+
+      if (isWhitespace(modifiedChunk)) {
+        this.logger.debug('TtsStreamingBuffer:_feedQueue modified chunk is only whitespace, restoring queue');
+        this.queue.unshift({ type: 'text', value: chunk });
+        this.bufferedLength += chunkEnd;
+        this._setTimerIfNeeded();
+        return;
+      }
       this.logger.debug(`TtsStreamingBuffer:_feedQueue sending chunk to tts: ${modifiedChunk}`);
 
       try {
@@ -349,6 +362,7 @@ class TtsStreamingBuffer extends Emitter {
     if (this.queue.length > 0) {
       await this._feedQueue();
     }
+    this.emit(TtsStreamingEvents.Connected, { vendor });
   }
 
   _onConnectFailure(vendor) {
@@ -399,6 +413,7 @@ class TtsStreamingBuffer extends Emitter {
 
   removeCustomEventListeners() {
     this.eventHandlers.forEach((h) => h.ep.removeCustomEventListener(h.event, h.handler));
+    this.eventHandlers.length = 0;
   }
 
   _initHandlers(ep) {
@@ -422,7 +437,15 @@ class TtsStreamingBuffer extends Emitter {
 
 const findSentenceBoundary = (text, limit) => {
   // Look for punctuation or double newline that signals sentence end.
-  const sentenceEndRegex = /[.!?](?=\s|$)|\n\n/g;
+  // Includes:
+  //   - ASCII: . ! ?
+  //   - Arabic: ؟ (question mark), ۔ (full stop)
+  //   - Japanese: 。 (full stop), ！, ？ (full-width exclamation/question)
+  //
+  // For languages that use spaces between sentences, we still require
+  // whitespace or end-of-string after the mark. For Japanese (no spaces),
+  // we treat the punctuation itself as a boundary regardless of following char.
+  const sentenceEndRegex = /[.!?؟۔](?=\s|$)|[。！？]|\n\n/g;
   let lastSentenceBoundary = -1;
   let match;
   while ((match = sentenceEndRegex.exec(text)) && match.index < limit) {

package.json

@@ -27,14 +27,14 @@
   "dependencies": {
     "@aws-sdk/client-auto-scaling": "^3.549.0",
     "@aws-sdk/client-sns": "^3.549.0",
-    "@jambonz/db-helpers": "^0.9.17",
+    "@jambonz/db-helpers": "^0.9.18",
     "@jambonz/http-health-check": "^0.0.1",
     "@jambonz/mw-registrar": "^0.2.7",
     "@jambonz/realtimedb-helpers": "^0.8.15",
-    "@jambonz/speech-utils": "^0.2.24",
+    "@jambonz/speech-utils": "^0.2.26",
     "@jambonz/stats-collector": "^0.1.10",
-    "@jambonz/time-series": "^0.2.14",
-    "@jambonz/verb-specifications": "^0.0.116",
+    "@jambonz/time-series": "^0.2.15",
+    "@jambonz/verb-specifications": "^0.0.122",
     "@modelcontextprotocol/sdk": "^1.9.0",
     "@opentelemetry/api": "^1.8.0",
     "@opentelemetry/exporter-jaeger": "^1.23.0",
@@ -49,12 +49,12 @@
     "debug": "^4.3.4",
     "deepcopy": "^2.1.0",
     "drachtio-fsmrf": "^4.1.2",
-    "drachtio-srf": "^5.0.11",
+    "drachtio-srf": "^5.0.14",
     "express": "^4.19.2",
     "express-validator": "^7.0.1",
     "moment": "^2.30.1",
     "parse-url": "^9.2.0",
-    "pino": "^8.20.0",
+    "pino": "^10.1.0",
     "polly-ssml-split": "^0.1.0",
     "sdp-transform": "^2.15.0",
     "short-uuid": "^5.1.0",

test/index.js

@@ -4,6 +4,7 @@ require('./ws-requestor-unit-test');
 require('./http-requestor-retry-test');
 require('./http-requestor-unit-test');
 require('./unit-tests');
+require('./tts-streaming-buffer-test');
 require('./docker_start');
 require('./create-test-db');
 require('./account-validation-tests');

test/tts-streaming-buffer-test.js

@@ -0,0 +1,177 @@
+const test = require('tape');
+const sinon = require('sinon');
+
+const noop = () => {};
+const logger = {
+  error: noop,
+  info: noop,
+  debug: noop
+};
+
+const {
+  TtsStreamingConnectionStatus
+} = require('../lib/utils/constants.json');
+
+const TtsStreamingBuffer = require('../lib/utils/tts-streaming-buffer');
+
+// Helper to create a mock CallSession
+function createMockCs(options = {}) {
+  const mockEp = {
+    uuid: 'test-uuid-1234',
+    api: sinon.stub().resolves({ body: '+OK' }),
+    addCustomEventListener: sinon.stub(),
+    removeCustomEventListener: sinon.stub()
+  };
+
+  return {
+    logger,
+    ep: mockEp,
+    isTtsStreamOpen: options.isTtsStreamOpen !== undefined ? options.isTtsStreamOpen : true,
+    getTsStreamingVendor: () => options.vendor || 'deepgram'
+  };
+}
+
+/**
+ * BUG REPRODUCTION TEST
+ *
+ * This test reproduces the exact issue from production logs:
+ * {
+ *   "args": ["uuid", "send", " "],
+ *   "msg": "Error calling uuid_deepgram_tts_streaming: -USAGE: <uuid> connect|send|clear|close [tokens]"
+ * }
+ *
+ * Root cause: When multiple flushes are queued while connecting, and a space token
+ * gets buffered between flushes, Phase 1 of _feedQueue sends that space to the TTS vendor.
+ *
+ * Sequence:
+ * 1. bufferTokens('Hello.') while connecting
+ * 2. flush() while connecting
+ * 3. bufferTokens(' ') while connecting (passes because bufferedLength > 0)
+ * 4. flush() while connecting
+ * 5. Connection completes, _feedQueue processes: [text:Hello., flush, text:" ", flush]
+ * 6. First flush sends "Hello." - OK
+ * 7. Second flush sends " " - BUG!
+ */
+test('TtsStreamingBuffer: multiple flushes while connecting - space token sent to TTS vendor', async(t) => {
+  const cs = createMockCs();
+  const buffer = new TtsStreamingBuffer(cs);
+
+  buffer._connectionStatus = TtsStreamingConnectionStatus.Connecting;
+  buffer.vendor = 'deepgram';
+
+  const apiCalls = [];
+  const originalApi = buffer._api.bind(buffer);
+  buffer._api = async function(ep, args) {
+    apiCalls.push({ args: [...args] });
+    return originalApi(ep, args);
+  };
+
+  // First batch while connecting
+  await buffer.bufferTokens('Hello.');
+  buffer.flush();
+
+  // Second batch - just a space (passes because bufferedLength > 0)
+  await buffer.bufferTokens(' ');
+  buffer.flush();
+
+  // Verify queue state before connect
+  t.equal(buffer.queue.length, 4, 'queue should have 4 items: [text, flush, text, flush]');
+  t.equal(buffer.queue[0].type, 'text', 'first item should be text');
+  t.equal(buffer.queue[0].value, 'Hello.', 'first text should be "Hello."');
+  t.equal(buffer.queue[1].type, 'flush', 'second item should be flush');
+  t.equal(buffer.queue[2].type, 'text', 'third item should be text');
+  t.equal(buffer.queue[2].value, ' ', 'third item should be space');
+  t.equal(buffer.queue[3].type, 'flush', 'fourth item should be flush');
+
+  // Connect - triggers _feedQueue
+  buffer._connectionStatus = TtsStreamingConnectionStatus.Connected;
+  await buffer._feedQueue();
+
+  // Check API calls
+  const sendCalls = apiCalls.filter(call => call.args[1] === 'send');
+
+  // This assertion will FAIL until the bug is fixed
+  const whitespaceOnlySends = sendCalls.filter(call => /^\s*$/.test(call.args[2]));
+
+  t.equal(whitespaceOnlySends.length, 0,
+    `should not send whitespace-only tokens, but sent: ${whitespaceOnlySends.map(c => JSON.stringify(c.args[2])).join(', ')}`);
+
+  t.end();
+});
+
+/**
+ * Additional test: Verify text with trailing space in same flush is OK
+ */
+test('TtsStreamingBuffer: text with trailing space in same flush should work', async(t) => {
+  const cs = createMockCs();
+  const buffer = new TtsStreamingBuffer(cs);
+
+  buffer._connectionStatus = TtsStreamingConnectionStatus.Connecting;
+  buffer.vendor = 'deepgram';
+
+  const apiCalls = [];
+  const originalApi = buffer._api.bind(buffer);
+  buffer._api = async function(ep, args) {
+    apiCalls.push({ args: [...args] });
+    return originalApi(ep, args);
+  };
+
+  // Buffer text with trailing space, then flush
+  await buffer.bufferTokens('Hello.');
+  await buffer.bufferTokens(' ');
+  buffer.flush();
+
+  // Connect
+  buffer._connectionStatus = TtsStreamingConnectionStatus.Connected;
+  await buffer._feedQueue();
+
+  const sendCalls = apiCalls.filter(call => call.args[1] === 'send');
+
+  t.equal(sendCalls.length, 1, 'should have one send call');
+  t.equal(sendCalls[0].args[2], 'Hello. ', 'should send "Hello. " (text with trailing space)');
+
+  t.end();
+});
+
+/**
+ * Test: Leading whitespace should be discarded when buffer is empty
+ */
+test('TtsStreamingBuffer: leading whitespace discarded when buffer empty', async(t) => {
+  const cs = createMockCs();
+  const buffer = new TtsStreamingBuffer(cs);
+
+  buffer._connectionStatus = TtsStreamingConnectionStatus.Connected;
+  buffer.vendor = 'deepgram';
+
+  // Try to buffer whitespace when buffer is empty
+  const result = await buffer.bufferTokens('   ');
+
+  t.equal(result.status, 'ok', 'should return ok status');
+  t.equal(buffer.bufferedLength, 0, 'buffer should remain empty');
+  t.equal(buffer.queue.length, 0, 'queue should remain empty');
+
+  t.end();
+});
+
+/**
+ * Test: Whitespace can be buffered when buffer has content
+ */
+test('TtsStreamingBuffer: whitespace accepted when buffer has content', async(t) => {
+  const cs = createMockCs();
+  const buffer = new TtsStreamingBuffer(cs);
+
+  buffer._connectionStatus = TtsStreamingConnectionStatus.Connecting;
+  buffer.vendor = 'deepgram';
+
+  // Buffer real text first
+  await buffer.bufferTokens('Hello');
+
+  // Now buffer whitespace (should pass because bufferedLength > 0)
+  const result = await buffer.bufferTokens(' ');
+
+  t.equal(result.status, 'ok', 'should return ok status');
+  t.equal(buffer.bufferedLength, 6, 'buffer should have 6 chars');
+  t.equal(buffer.queue.length, 2, 'queue should have 2 items');
+
+  t.end();
+});

test/webhooks-tests.js

@@ -83,7 +83,8 @@ test('invalid jambonz json create alert tests', async(t) => {
       {account_sid: 'bb845d4b-83a9-4cde-a6e9-50f3743bab3f', page: 1, page_size: 25, days: 7});
     let checked = false;
     for (let i = 0; i < data.total; i++) {
-      checked = data.data[i].message === 'malformed jambonz payload: must be array'
+      checked = data.data[i].message === 'malformed jambonz payload: must be array';
+      if (checked) break;
     }
     t.ok(checked, 'alert is raised as expected');
     disconnect();