Google cloud video intelligence can't annotate multiple features

I've been using Google Cloud Video Intelligence for text detection. Now, I want to use it for speech transcription so I added SPEECH_TRANSCRIPTION feature to TEXT_DETECTION but the response only contains result for one feature, the last one.

const gcsUri = 'gs://path-to-the-video-on-gcs'
const request = {
  inputUri: gcsUri,
  features: ['TEXT_DETECTION', 'SPEECH_TRANSCRIPTION'],
};

// Detects text in a video
const [operation] = await video.annotateVideo(request);
const [operationResult] = await operation.promise();

const annotationResult = operationResult.annotationResults[0]
const textAnnotations  = annotationResult.textAnnotations
const speechTranscriptions  = annotationResult.speechTranscriptions

console.log(textAnnotations) // --> []
console.log(speechTranscriptions) // --> [{...}]

Is this a case where annotation is performed on only one feature at a time?

Annotation will be performed for both features. Below is an example code.

const videoIntelligence = require('@google-cloud/video-intelligence');
const client = new videoIntelligence.VideoIntelligenceServiceClient();
const gcsUri = 'gs://cloud-samples-data/video/JaneGoodall.mp4';


async function analyzeVideoTranscript() {
const videoContext = {
 speechTranscriptionConfig: {
   languageCode: 'en-US',
   enableAutomaticPunctuation: true,
 },
};


const request = {
 inputUri: gcsUri,
 features: ['TEXT_DETECTION','SPEECH_TRANSCRIPTION'],
 videoContext: videoContext,
};


const [operation] = await client.annotateVideo(request);
const results = await operation.promise();
console.log('Waiting for operation to complete...');
// Gets annotations for video
console.log('Result------------------->');
console.log(results[0].annotationResults);


var i=1;
results[0].annotationResults.forEach(annotationResult=> {
   console.log("annotation result no: "+i+" =======================>")
   console.log("Speech : "+annotationResult.speechTranscriptions);       
   console.log("Text: "+annotationResult.textAnnotations);
   i++;
});


}
analyzeVideoTranscript();

N.B: What I have found is that annotationResult may not return the result in the same order of the declared features . You may want to change the code accordingly as per your need.

Edit:

You can check how many results you are getting by printing the results.annotationResults.length .
You should have two annotation results for the individual features. All you need to do is to traverse the response.

Here is the output of the above code:

Output got converted to string as I have printed the result in the same line.

I think it has to do with the async call and the ... spread operator. I tested this with all the features to be sure and it worked for me.

const { VideoIntelligenceServiceClient } = require('@google-cloud/video- 
intelligence');
const path = require('path');
const gcsUri = 'gs://path/somefile';
const outputUri = `gs://optional-path-to-save-check-bucket}.json`;
const videoClient = new VideoIntelligenceServiceClient({
keyFilename: '/path_to_local/key/used/to_test_this.json'
});
const transcriptConfig = {
languageCode: "en-US",
enableAutomaticPunctuation: true,
enableSpeakerDiarization: true,
enableWordConfidence: true,
speechContexts: []
};
const videoContext = {
speechTranscriptionConfig: transcriptConfig,
};
//Threw in all features to check myself
const request = {
inputUri: gcsUri,
outputUri: outputUri,
features: [ 'OBJECT_TRACKING',
'LABEL_DETECTION',
'SHOT_CHANGE_DETECTION',
'TEXT_DETECTION',
'FACE_DETECTION',
'PERSON_DETECTION',
'LOGO_RECOGNITION',
'EXPLICIT_CONTENT_DETECTION',
'SPEECH_TRANSCRIPTION'],
videoContext: videoContext
};
async function detectTextAndSpeech() {
// Detects text and speech in a video
const [operation] = await videoClient.annotateVideo(request);
const [operationResult] = await operation.promise();
const textAnnotations = [];
const speechTranscriptions = [];
operationResult.annotationResults.forEach(annotationResult => {
if (annotationResult.textAnnotations) {
textAnnotations.push(...annotationResult.textAnnotations);
}
if (annotationResult.speechTranscriptions) {
speechTranscriptions.push(...annotationResult.speechTranscriptions);
}
});
console.log(textAnnotations);
console.log(speechTranscriptions);
}
detectTextAndSpeech();