feat(stt-tts): generation release changes

watson-developer-cloud · May 26, 2021 · 1bc946b · 1bc946b
1 parent 8e70b7f
commit 1bc946b
Show file tree

Hide file tree

Showing 6 changed files with 1,818 additions and 167 deletions.
diff --git a/speech-to-text/v1-generated.ts b/speech-to-text/v1-generated.ts
diff --git a/test/integration/text-to-speech.test.js b/test/integration/text-to-speech.test.js
@@ -2,6 +2,8 @@
 
 const { IamAuthenticator } = require('../../dist/auth');
 const TextToSpeechV1 = require('../../dist/text-to-speech/v1');
+const fs = require('fs');
+const path = require('path');
 const wav = require('wav');
 const authHelper = require('../resources/auth_helper.js');
 const describe = authHelper.describe; // this runs describe.skip if there is no auth.js file :)
@@ -94,6 +96,66 @@ describe('text to speech_integration', () => {
       customizationId = result.customization_id;
     });
 
+    describe('custom prompts', () => {
+      const promptId = 'Hello';
+
+      it('should addCustomPrompt()', async () => {
+        expect(customizationId).toBeTruthy();
+
+        const params = {
+          customizationId,
+          promptId,
+          metadata: {
+            prompt_text: 'Hello, how are you today?',
+          },
+          file: fs.createReadStream(path.join(__dirname, '../resources/tts_audio.wav')),
+          filename: 'tts_audio.wav',
+        };
+
+        const res = await textToSpeech.addCustomPrompt(params);
+        const { result } = res || {};
+        expect(result.prompt_id).toBe('Hello');
+      });
+
+      it('should listCustomPrompts()', async () => {
+        expect(customizationId).toBeTruthy();
+
+        const params = {
+          customizationId,
+        };
+
+        const res = await textToSpeech.listCustomPrompts(params);
+        const { result } = res || {};
+        expect(result.prompts.length).toBeTruthy();
+      });
+
+      it('should getCustomPrompt()', async () => {
+        expect(customizationId).toBeTruthy();
+
+        const params = {
+          customizationId,
+          promptId,
+        };
+
+        const res = await textToSpeech.getCustomPrompt(params);
+        const { result } = res || {};
+        expect(result.prompt_id).toBe('Hello');
+      });
+
+      it('should deleteCustomPrompt()', async () => {
+        expect(customizationId).toBeTruthy();
+
+        const params = {
+          customizationId,
+          promptId,
+        };
+
+        const res = await textToSpeech.deleteCustomPrompt(params);
+        const { result } = res || {};
+        expect(result).toBeDefined();
+      });
+    });
+
     it('should listCustomModels() with language', async () => {
       const params = {
         language: 'en-GB',
@@ -220,4 +282,52 @@ describe('text to speech_integration', () => {
       expect(result).toBeDefined();
     });
   });
+
+  describe('speaker models', () => {
+    let speakerId;
+
+    it('should createSpeakerModel()', async () => {
+      const params = {
+        speakerName: 'Angelo',
+        audio: fs.createReadStream(path.join(__dirname, '../resources/tts_audio.wav')),
+      };
+
+      const res = await textToSpeech.createSpeakerModel(params);
+      const { result } = res || {};
+      expect(result.speaker_id).toBeDefined();
+      speakerId = result.speaker_id;
+    });
+
+    it('should listSpeakerModels()', async () => {
+      expect(speakerId).toBeTruthy();
+
+      const res = await textToSpeech.listSpeakerModels();
+      const { result } = res || {};
+      expect(result.speakers.length).toBeTruthy();
+    });
+
+    it('should getSpeakerModel()', async () => {
+      expect(speakerId).toBeTruthy();
+
+      const params = {
+        speakerId,
+      };
+
+      const res = await textToSpeech.getSpeakerModel(params);
+      const { result } = res || {};
+      expect(result.customizations).toBeDefined();
+    });
+
+    it('should deleteSpeakerModel()', async () => {
+      expect(speakerId).toBeTruthy();
+
+      const params = {
+        speakerId,
+      };
+
+      const res = await textToSpeech.deleteSpeakerModel(params);
+      const { result } = res || {};
+      expect(result).toBeDefined();
+    });
+  });
 });
diff --git a/test/resources/tts_audio.wav b/test/resources/tts_audio.wav
diff --git a/test/unit/speech-to-text.v1.test.js b/test/unit/speech-to-text.v1.test.js
@@ -1,5 +1,5 @@
 /**
- * (C) Copyright IBM Corp. 2018, 2020.
+ * (C) Copyright IBM Corp. 2018, 2021.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -253,6 +253,7 @@ describe('SpeechToTextV1', () => {
         const splitTranscriptAtPhraseEnd = true;
         const speechDetectorSensitivity = 36.0;
         const backgroundAudioSuppression = 36.0;
+        const lowLatency = true;
         const params = {
           audio: audio,
           contentType: contentType,
@@ -279,6 +280,7 @@ describe('SpeechToTextV1', () => {
           splitTranscriptAtPhraseEnd: splitTranscriptAtPhraseEnd,
           speechDetectorSensitivity: speechDetectorSensitivity,
           backgroundAudioSuppression: backgroundAudioSuppression,
+          lowLatency: lowLatency,
         };
 
         const recognizeResult = speechToTextService.recognize(params);
@@ -320,6 +322,7 @@ describe('SpeechToTextV1', () => {
         expect(options.qs['split_transcript_at_phrase_end']).toEqual(splitTranscriptAtPhraseEnd);
         expect(options.qs['speech_detector_sensitivity']).toEqual(speechDetectorSensitivity);
         expect(options.qs['background_audio_suppression']).toEqual(backgroundAudioSuppression);
+        expect(options.qs['low_latency']).toEqual(lowLatency);
       });
 
       test('should prioritize user-given headers', () => {
@@ -538,6 +541,7 @@ describe('SpeechToTextV1', () => {
         const splitTranscriptAtPhraseEnd = true;
         const speechDetectorSensitivity = 36.0;
         const backgroundAudioSuppression = 36.0;
+        const lowLatency = true;
         const params = {
           audio: audio,
           contentType: contentType,
@@ -570,6 +574,7 @@ describe('SpeechToTextV1', () => {
           splitTranscriptAtPhraseEnd: splitTranscriptAtPhraseEnd,
           speechDetectorSensitivity: speechDetectorSensitivity,
           backgroundAudioSuppression: backgroundAudioSuppression,
+          lowLatency: lowLatency,
         };
 
         const createJobResult = speechToTextService.createJob(params);
@@ -617,6 +622,7 @@ describe('SpeechToTextV1', () => {
         expect(options.qs['split_transcript_at_phrase_end']).toEqual(splitTranscriptAtPhraseEnd);
         expect(options.qs['speech_detector_sensitivity']).toEqual(speechDetectorSensitivity);
         expect(options.qs['background_audio_suppression']).toEqual(backgroundAudioSuppression);
+        expect(options.qs['low_latency']).toEqual(lowLatency);
       });
 
       test('should prioritize user-given headers', () => {