support gladia stt (#1397)

* support gladia stt

* wip

* wip

* update verb specification

lib/utils/transcription-utils.js

@@ -376,6 +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));
 
@@ -742,6 +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':
@@ -1059,6 +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;