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 <henryheng@flowiseai.com>
Co-authored-by: Henry <hzj94@hotmail.com>

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