Feature/Add Azure Cognitive speech-to-text functionality (#3718)

* feat: Add Azure Cognitive Services integration for speech-to-text functionality

- Introduced a new credential class for Azure Cognitive Services.
- Updated speech-to-text processing to support Azure Cognitive Services as a provider.
- Enhanced UI components to include Azure Cognitive Services options and inputs for configuration.
- Added necessary imports and error handling for Azure API requests.

* Update SpeechToText.jsx linting

* refactor: Update audio file handling in SpeechToText component

- Removed the dependency on 'form-data' and replaced it with a Blob for audio file uploads.
- Simplified the audio file appending process to the form data.
- Cleaned up the headers in the Axios request by removing unnecessary form data headers.

This change enhances the efficiency of audio file processing in the speech-to-text functionality.

---------

Co-authored-by: Henry Heng <[email protected]>
Co-authored-by: Henry <[email protected]>

packages/components/credentials/AzureCognitiveServices.credential.ts

@@ -0,0 +1,39 @@
+import { INodeParams, INodeCredential } from '../src/Interface'
+
+class AzureCognitiveServices implements INodeCredential {
+    label: string
+    name: string
+    version: number
+    inputs: INodeParams[]
+
+    constructor() {
+        this.label = 'Azure Cognitive Services'
+        this.name = 'azureCognitiveServices'
+        this.version = 1.0
+        this.inputs = [
+            {
+                label: 'Azure Subscription Key',
+                name: 'azureSubscriptionKey',
+                type: 'password',
+                description: 'Your Azure Cognitive Services subscription key'
+            },
+            {
+                label: 'Service Region',
+                name: 'serviceRegion',
+                type: 'string',
+                description: 'The Azure service region (e.g., "westus", "eastus")',
+                placeholder: 'westus'
+            },
+            {
+                label: 'API Version',
+                name: 'apiVersion',
+                type: 'string',
+                description: 'The API version to use (e.g., "2024-05-15-preview")',
+                placeholder: '2024-05-15-preview',
+                default: '2024-05-15-preview'
+            }
+        ]
+    }
+}
+
+module.exports = { credClass: AzureCognitiveServices }

packages/components/src/speechToText.ts

@@ -3,12 +3,14 @@ import { getCredentialData } from './utils'
 import { type ClientOptions, OpenAIClient, toFile } from '@langchain/openai'
 import { AssemblyAI } from 'assemblyai'
 import { getFileFromStorage } from './storageUtils'
+import axios from 'axios'
 import Groq from 'groq-sdk'
 
 const SpeechToTextType = {
     OPENAI_WHISPER: 'openAIWhisper',
     ASSEMBLYAI_TRANSCRIBE: 'assemblyAiTranscribe',
     LOCALAI_STT: 'localAISTT',
+    AZURE_COGNITIVE: 'azureCognitive',
     GROQ_WHISPER: 'groqWhisper'
 }
 
@@ -72,6 +74,40 @@ export const convertSpeechToText = async (upload: IFileUpload, speechToTextConfi
                 }
                 break
             }
+            case SpeechToTextType.AZURE_COGNITIVE: {
+                try {
+                    const baseUrl = `https://${credentialData.serviceRegion}.cognitiveservices.azure.com/speechtotext/transcriptions:transcribe`
+                    const apiVersion = credentialData.apiVersion || '2024-05-15-preview'
+
+                    const formData = new FormData()
+                    const audioBlob = new Blob([audio_file], { type: upload.type })
+                    formData.append('audio', audioBlob, upload.name)
+
+                    const channelsStr = speechToTextConfig.channels || '0,1'
+                    const channels = channelsStr.split(',').map(Number)
+
+                    const definition = {
+                        locales: [speechToTextConfig.language || 'en-US'],
+                        profanityFilterMode: speechToTextConfig.profanityFilterMode || 'Masked',
+                        channels
+                    }
+                    formData.append('definition', JSON.stringify(definition))
+
+                    const response = await axios.post(`${baseUrl}?api-version=${apiVersion}`, formData, {
+                        headers: {
+                            'Ocp-Apim-Subscription-Key': credentialData.azureSubscriptionKey,
+                            Accept: 'application/json'
+                        }
+                    })
+
+                    if (response.data && response.data.combinedPhrases.length > 0) {
+                        return response.data.combinedPhrases[0]?.text || ''
+                    }
+                    return ''
+                } catch (error) {
+                    throw error.response?.data || error
+                }
+            }
             case SpeechToTextType.GROQ_WHISPER: {
                 const groqClient = new Groq({
                     apiKey: credentialData.groqApiKey

packages/ui/src/ui-component/extended/SpeechToText.jsx

@@ -17,6 +17,7 @@ import { Dropdown } from '@/ui-component/dropdown/Dropdown'
 import openAISVG from '@/assets/images/openai.svg'
 import assemblyAIPng from '@/assets/images/assemblyai.png'
 import localAiPng from '@/assets/images/localai.png'
+import azureSvg from '@/assets/images/azure_openai.svg'
 import groqPng from '@/assets/images/groq.png'
 
 // store
@@ -31,6 +32,7 @@ const SpeechToTextType = {
     OPENAI_WHISPER: 'openAIWhisper',
     ASSEMBLYAI_TRANSCRIBE: 'assemblyAiTranscribe',
     LOCALAI_STT: 'localAISTT',
+    AZURE_COGNITIVE: 'azureCognitive',
     GROQ_WHISPER: 'groqWhisper'
 }
 
@@ -142,6 +144,58 @@ const speechToTextProviders = {
             }
         ]
     },
+    [SpeechToTextType.AZURE_COGNITIVE]: {
+        label: 'Azure Cognitive Services',
+        name: SpeechToTextType.AZURE_COGNITIVE,
+        icon: azureSvg,
+        url: 'https://azure.microsoft.com/en-us/products/cognitive-services/speech-services',
+        inputs: [
+            {
+                label: 'Connect Credential',
+                name: 'credential',
+                type: 'credential',
+                credentialNames: ['azureCognitiveServices']
+            },
+            {
+                label: 'Language',
+                name: 'language',
+                type: 'string',
+                description: 'The recognition language (e.g., "en-US", "es-ES")',
+                placeholder: 'en-US',
+                optional: true
+            },
+            {
+                label: 'Profanity Filter Mode',
+                name: 'profanityFilterMode',
+                type: 'options',
+                description: 'How to handle profanity in the transcription',
+                options: [
+                    {
+                        label: 'None',
+                        name: 'None'
+                    },
+                    {
+                        label: 'Masked',
+                        name: 'Masked'
+                    },
+                    {
+                        label: 'Removed',
+                        name: 'Removed'
+                    }
+                ],
+                default: 'Masked',
+                optional: true
+            },
+            {
+                label: 'Audio Channels',
+                name: 'channels',
+                type: 'string',
+                description: 'Comma-separated list of audio channels to process (e.g., "0,1")',
+                placeholder: '0,1',
+                default: '0,1'
+            }
+        ]
+    },
     [SpeechToTextType.GROQ_WHISPER]: {
         label: 'Groq Whisper',
         name: SpeechToTextType.GROQ_WHISPER,