support gladia stt (#1397)

* support gladia stt

* wip

* wip

* update verb specification

lib/session/call-session.js

@@ -1086,6 +1086,13 @@ 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,

lib/tasks/gather.js

@@ -5,6 +5,7 @@ const {
   AwsTranscriptionEvents,
   AzureTranscriptionEvents,
   DeepgramTranscriptionEvents,
+  GladiaTranscriptionEvents,
   SonioxTranscriptionEvents,
   CobaltTranscriptionEvents,
   IbmTranscriptionEvents,
@@ -487,6 +488,16 @@ 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(

lib/tasks/stt-task.js

@@ -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) {

lib/tasks/transcribe.js

@@ -6,6 +6,7 @@ const {
   AwsTranscriptionEvents,
   AzureTranscriptionEvents,
   DeepgramTranscriptionEvents,
+  GladiaTranscriptionEvents,
   DeepgramfluxTranscriptionEvents,
   SonioxTranscriptionEvents,
   CobaltTranscriptionEvents,
@@ -255,6 +256,18 @@ 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`;

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"

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;

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;

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": "^0.0.117",
+        "@jambonz/verb-specifications": "^0.0.118",
         "@modelcontextprotocol/sdk": "^1.9.0",
         "@opentelemetry/api": "^1.8.0",
         "@opentelemetry/exporter-jaeger": "^1.23.0",
@@ -1517,9 +1517,9 @@
       }
     },
     "node_modules/@jambonz/verb-specifications": {
-      "version": "0.0.117",
-      "resolved": "https://registry.npmjs.org/@jambonz/verb-specifications/-/verb-specifications-0.0.117.tgz",
-      "integrity": "sha512-yfnHWfqVRyE9ICBdVQV8CFwj0jDInpgMYdv9lI5c4iOmnYrJU3e/iFdrwM+abhFyZGL1Can9onynPW6RZFXXsw==",
+      "version": "0.0.118",
+      "resolved": "https://registry.npmjs.org/@jambonz/verb-specifications/-/verb-specifications-0.0.118.tgz",
+      "integrity": "sha512-1dGnc6TUCehjt1yGNuqh1uzk1xw9HhUm39aVUosQMHlnT0fK0ItikeJ0uttTjFastHNmPPxqJwb20wOvVGTCFg==",
       "license": "MIT",
       "dependencies": {
         "debug": "^4.3.4",

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": "^0.0.117",
+    "@jambonz/verb-specifications": "^0.0.118",
     "@modelcontextprotocol/sdk": "^1.9.0",
     "@opentelemetry/api": "^1.8.0",
     "@opentelemetry/exporter-jaeger": "^1.23.0",