support houndify stt (#1364)

* support houndify stt

* wip

* wip

* wip

* update houndify stt parameters

* wip

* wip

lib/session/call-session.js

@@ -1166,6 +1166,14 @@ 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
+          };
+        }
         else if ('deepgramflux' === vendor) {
           return {
             speech_credential_sid: credential.speech_credential_sid,

lib/tasks/gather.js

@@ -11,6 +11,7 @@ const {
   NvidiaTranscriptionEvents,
   JambonzTranscriptionEvents,
   AssemblyAiTranscriptionEvents,
+  HoundifyTranscriptionEvents,
   DeepgramfluxTranscriptionEvents,
   VoxistTranscriptionEvents,
   CartesiaTranscriptionEvents,
@@ -563,6 +564,18 @@ 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,

lib/tasks/transcribe.js

@@ -14,6 +14,7 @@ const {
   JambonzTranscriptionEvents,
   TranscribeStatus,
   AssemblyAiTranscriptionEvents,
+  HoundifyTranscriptionEvents,
   VoxistTranscriptionEvents,
   CartesiaTranscriptionEvents,
   OpenAITranscriptionEvents,
@@ -324,6 +325,18 @@ 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,

lib/utils/constants.json

@@ -169,6 +169,12 @@
     "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",

lib/utils/db-utils.js

@@ -142,6 +142,12 @@ 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;
+    }
     else if ('voxist' === obj.vendor) {
       const o = JSON.parse(decrypt(credential));
       obj.api_key = o.api_key;

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'
+  ],
 };
 
 /**
@@ -582,6 +619,30 @@ 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 {
@@ -701,6 +762,8 @@ 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':
@@ -1122,6 +1185,57 @@ 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
+      } = rOpts.houndifyOptions || {};
+
+      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}),
+        ...(audioEndpoint && {HOUNDIFY_AUDIO_ENDPOINT: audioEndpoint}),
+        ...(customVocabulary && {HOUNDIFY_CUSTOM_VOCABULARY:
+          Array.isArray(customVocabulary) ? customVocabulary.join(',') : customVocabulary}),
+        ...(languageModel && {HOUNDIFY_LANGUAGE_MODEL: languageModel}),
+      };
+    }
     else if ('voxist' === vendor) {
       opts = {
         ...opts,

package-lock.json

@@ -18,7 +18,7 @@
         "@jambonz/speech-utils": "^0.2.25",
         "@jambonz/stats-collector": "^0.1.10",
         "@jambonz/time-series": "^0.2.14",
-        "@jambonz/verb-specifications": "^0.0.116",
+        "@jambonz/verb-specifications": "^0.0.117",
         "@modelcontextprotocol/sdk": "^1.9.0",
         "@opentelemetry/api": "^1.8.0",
         "@opentelemetry/exporter-jaeger": "^1.23.0",
@@ -1521,9 +1521,10 @@
       }
     },
     "node_modules/@jambonz/verb-specifications": {
-      "version": "0.0.116",
+      "version": "0.0.117",
-      "resolved": "https://registry.npmjs.org/@jambonz/verb-specifications/-/verb-specifications-0.0.116.tgz",
+      "resolved": "https://registry.npmjs.org/@jambonz/verb-specifications/-/verb-specifications-0.0.117.tgz",
-      "integrity": "sha512-EFAtwSpSWA12nk7eQfAiWS0bGkCA5+NqKsylnVIXNWuSjRZ5wTS0dAZZZxqtZxPZ1DxdBLCafbLsKZJ4fkC+tQ==",
+      "integrity": "sha512-yfnHWfqVRyE9ICBdVQV8CFwj0jDInpgMYdv9lI5c4iOmnYrJU3e/iFdrwM+abhFyZGL1Can9onynPW6RZFXXsw==",
+      "license": "MIT",
       "dependencies": {
         "debug": "^4.3.4",
         "pino": "^8.8.0"

package.json

@@ -34,7 +34,7 @@
     "@jambonz/speech-utils": "^0.2.25",
     "@jambonz/stats-collector": "^0.1.10",
     "@jambonz/time-series": "^0.2.14",
-    "@jambonz/verb-specifications": "^0.0.116",
+    "@jambonz/verb-specifications": "^0.0.117",
     "@modelcontextprotocol/sdk": "^1.9.0",
     "@opentelemetry/api": "^1.8.0",
     "@opentelemetry/exporter-jaeger": "^1.23.0",