Merge pull request #6088 from eric-urban/eur/ai-speech-diarization-ts

Get started with speech to text diarization using TypeScript

Author: v-ccolin

articles/ai-services/speech-service/get-started-stt-diarization.md

@@ -7,9 +7,9 @@ manager: nitinme
 ms.service: azure-ai-speech
 ms.custom: devx-track-extended-java, devx-track-go, devx-track-js, devx-track-python
 ms.topic: quickstart
-ms.date: 3/10/2025
+ms.date: 7/16/2025
 ms.author: eur
-zone_pivot_groups: programming-languages-speech-services
+zone_pivot_groups: programming-languages-speech-diarization
 keywords: speech to text, speech to text software
 #customer intent: As a developer, I want to create speech to text applications that use diarization to identify speakers in multiple person conversations.
 ---
@@ -52,8 +52,8 @@ keywords: speech to text, speech to text software
 [!INCLUDE [REST include](includes/quickstarts/stt-diarization/rest.md)]
 ::: zone-end
 
-::: zone pivot="programming-language-cli"
-[!INCLUDE [CLI include](includes/quickstarts/stt-diarization/cli.md)]
+::: zone pivot="programming-language-typescript"
+[!INCLUDE [TypeScript include](includes/quickstarts/stt-diarization/typescript.md)]
 ::: zone-end
 
 ## Next step

articles/ai-services/speech-service/includes/quickstarts/speech-to-text-basics/javascript.md

@@ -47,33 +47,41 @@ To transcribe speech from a file:
 1. Create a new file named *transcription.js* with the following content:
 
     ```javascript
-    import { readFileSync } from "fs";
-    import { SpeechConfig, AudioConfig, SpeechRecognizer, ResultReason, CancellationDetails, CancellationReason } from "microsoft-cognitiveservices-speech-sdk";
+    import { readFileSync, createReadStream } from "fs";
+    import { SpeechConfig, AudioConfig, ConversationTranscriber, AudioInputStream } from "microsoft-cognitiveservices-speech-sdk";
     // This example requires environment variables named "SPEECH_KEY" and "SPEECH_REGION"
     const speechConfig = SpeechConfig.fromSubscription(process.env.SPEECH_KEY, process.env.SPEECH_REGION);
-    speechConfig.speechRecognitionLanguage = "en-US";
     function fromFile() {
-        const audioConfig = AudioConfig.fromWavFileInput(readFileSync("YourAudioFile.wav"));
-        const speechRecognizer = new SpeechRecognizer(speechConfig, audioConfig);
-        speechRecognizer.recognizeOnceAsync((result) => {
-            switch (result.reason) {
-                case ResultReason.RecognizedSpeech:
-                    console.log(`RECOGNIZED: Text=${result.text}`);
-                    break;
-                case ResultReason.NoMatch:
-                    console.log("NOMATCH: Speech could not be recognized.");
-                    break;
-                case ResultReason.Canceled:
-                    const cancellation = CancellationDetails.fromResult(result);
-                    console.log(`CANCELED: Reason=${cancellation.reason}`);
-                    if (cancellation.reason === CancellationReason.Error) {
-                        console.log(`CANCELED: ErrorCode=${cancellation.ErrorCode}`);
-                        console.log(`CANCELED: ErrorDetails=${cancellation.errorDetails}`);
-                        console.log("CANCELED: Did you set the speech resource key and region values?");
-                    }
-                    break;
-            }
-            speechRecognizer.close();
+        const filename = "katiesteve.wav";
+        const audioConfig = AudioConfig.fromWavFileInput(readFileSync(filename));
+        const conversationTranscriber = new ConversationTranscriber(speechConfig, audioConfig);
+        const pushStream = AudioInputStream.createPushStream();
+        createReadStream(filename).on('data', function (chunk) {
+            pushStream.write(chunk.slice());
+        }).on('end', function () {
+            pushStream.close();
+        });
+        console.log("Transcribing from: " + filename);
+        conversationTranscriber.sessionStarted = function (s, e) {
+            console.log("SessionStarted event");
+            console.log("SessionId:" + e.sessionId);
+        };
+        conversationTranscriber.sessionStopped = function (s, e) {
+            console.log("SessionStopped event");
+            console.log("SessionId:" + e.sessionId);
+            conversationTranscriber.stopTranscribingAsync();
+        };
+        conversationTranscriber.canceled = function (s, e) {
+            console.log("Canceled event");
+            console.log(e.errorDetails);
+            conversationTranscriber.stopTranscribingAsync();
+        };
+        conversationTranscriber.transcribed = function (s, e) {
+            console.log("TRANSCRIBED: Text=" + e.result.text + " Speaker ID=" + e.result.speakerId);
+        };
+        // Start conversation transcription
+        conversationTranscriber.startTranscribingAsync(function () { }, function (err) {
+            console.trace("err - starting transcription: " + err);
         });
     }
     fromFile();

articles/ai-services/speech-service/includes/quickstarts/stt-diarization/cli.md

@@ -2,7 +2,7 @@
 author: eric-urban
 ms.service: azure-ai-speech
 ms.topic: include
-ms.date: 3/10/2025
+ms.date: 7/16/2025
 ms.author: eur
 ---
 

articles/ai-services/speech-service/includes/quickstarts/stt-diarization/cpp.md

@@ -2,7 +2,7 @@
 author: eric-urban
 ms.service: azure-ai-speech
 ms.topic: include
-ms.date: 3/10/2025
+ms.date: 7/16/2025
 ms.author: eur
 ---
 

articles/ai-services/speech-service/includes/quickstarts/stt-diarization/csharp.md

@@ -2,7 +2,7 @@
 author: eric-urban
 ms.service: azure-ai-speech
 ms.topic: include
-ms.date: 3/10/2025
+ms.date: 7/16/2025
 ms.author: eur
 ---
 

articles/ai-services/speech-service/includes/quickstarts/stt-diarization/go.md

@@ -2,7 +2,7 @@
 author: eric-urban
 ms.service: azure-ai-speech
 ms.topic: include
-ms.date: 3/10/2025
+ms.date: 7/16/2025
 ms.author: eur
 ---
 

articles/ai-services/speech-service/includes/quickstarts/stt-diarization/intro.md

@@ -2,7 +2,7 @@
 author: eric-urban
 ms.service: azure-ai-speech
 ms.topic: include
-ms.date: 3/10/2025
+ms.date: 7/16/2025
 ms.author: eur
 ---
 

articles/ai-services/speech-service/includes/quickstarts/stt-diarization/java.md

@@ -2,7 +2,7 @@
 author: eric-urban
 ms.service: azure-ai-speech
 ms.topic: include
-ms.date: 3/10/2025
+ms.date: 7/16/2025
 ms.author: eur
 ---
 
@@ -14,49 +14,57 @@ ms.author: eur
 
 [!INCLUDE [Prerequisites](../../common/azure-prerequisites.md)]
 
-## Set up the environment
+## Setup
 
-To set up your environment, install the Speech SDK for JavaScript. If you just want the package name to install, run `npm install microsoft-cognitiveservices-speech-sdk`. For guided installation instructions, see the [SDK installation guide](../../../quickstarts/setup-platform.md?pivots=programming-language-javascript).
+1. Create a new folder `transcription-quickstart` and go to the quickstart folder with the following command:
 
-### Set environment variables
-
-[!INCLUDE [Environment variables](../../common/environment-variables.md)]
-
-## Implement diarization from file with conversation transcription
-
-Follow these steps to create a new console application for conversation transcription.
+    ```shell
+    mkdir transcription-quickstart && cd transcription-quickstart
+    ```
+    
+1. Create the `package.json` with the following command:
 
-1. Open a command prompt window where you want the new project, and create a new file named `ConversationTranscription.js`.
+    ```shell
+    npm init -y
+    ```
 
-1. Install the Speech SDK for JavaScript:
+1. Install the Speech SDK for JavaScript with:
 
     ```console
     npm install microsoft-cognitiveservices-speech-sdk
     ```
 
-1. Copy the following code into `ConversationTranscription.js`:
+### Retrieve resource information
+
+[!INCLUDE [Environment variables](../../common/environment-variables.md)]
+
+## Implement diarization from file with conversation transcription
+
+Follow these steps to create a new console application for conversation transcription.
+
+1. Create a new file named *transcription.js* with the following content:
 
     ```javascript
     const fs = require("fs");
     const sdk = require("microsoft-cognitiveservices-speech-sdk");
-
+    
     // This example requires environment variables named "SPEECH_KEY" and "SPEECH_REGION"
     const speechConfig = sdk.SpeechConfig.fromSubscription(process.env.SPEECH_KEY, process.env.SPEECH_REGION);
-
+    
     function fromFile() {
         const filename = "katiesteve.wav";
-
+    
         let audioConfig = sdk.AudioConfig.fromWavFileInput(fs.readFileSync(filename));
         let conversationTranscriber = new sdk.ConversationTranscriber(speechConfig, audioConfig);
-
+    
         var pushStream = sdk.AudioInputStream.createPushStream();
-        
+    
         fs.createReadStream(filename).on('data', function(arrayBuffer) {
             pushStream.write(arrayBuffer.slice());
         }).on('end', function() {
             pushStream.close();
         });
-        
+    
         console.log("Transcribing from: " + filename);
     
         conversationTranscriber.sessionStarted = function(s, e) {
@@ -76,15 +84,15 @@ Follow these steps to create a new console application for conversation transcri
         conversationTranscriber.transcribed = function(s, e) {
             console.log("TRANSCRIBED: Text=" + e.result.text + " Speaker ID=" + e.result.speakerId);
         };
-        
+    
         // Start conversation transcription
         conversationTranscriber.startTranscribingAsync(
             function () {},
             function (err) {
                 console.trace("err - starting transcription: " + err);
             }
         );
-
+    
     }
     fromFile();
     ```
@@ -98,11 +106,12 @@ Follow these steps to create a new console application for conversation transcri
 1. Run your new console application to start speech recognition from a file:
 
    ```console
-   node.exe ConversationTranscription.js
+   node transcription.js
    ```
 
-> [!IMPORTANT]
-> Make sure that you set the `SPEECH_KEY` and `SPEECH_REGION` [environment variables](#set-environment-variables). If you don't set these variables, the sample fails with an error message.
+Wait a few moments to get the response.
+
+## Output
 
 The transcribed conversation should be output as text:
 

articles/ai-services/speech-service/includes/quickstarts/stt-diarization/javascript.md

@@ -2,7 +2,7 @@
 author: eric-urban
 ms.service: azure-ai-speech
 ms.topic: include
-ms.date: 3/10/2025
+ms.date: 7/16/2025
 ms.author: eur
 ---