Month: March 2023

Convert Speech to Text using OpenAI Whisper in Power Apps

OpenAI has released a new neural network called Whisper, which is an open-source model that can convert speech to text with impressive accuracy. This model is specifically designed to transcribe spoken language into text with high precision and speed, making it an ideal tool for a variety of applications, such as virtual assistants and video captioning. Whisper relies on advanced machine learning algorithms to analyze audio signals from multiple languages and convert them into written text. OpenAI has recently made API endpoints available to the public since March 1, 2023, allowing developers to easily integrate this powerful technology into their own applications.

The Speech to Text Open API can

  • Transcribe audio into whatever language the audio is in.
  • Translate and transcribe the audio into English.

As of the date I am writing this post, this model is not available in Azure. In this blog post, I will cover how to use the Microphone control and File Upload control to convert speech to text using the OpenAI Whisper API in a Power Automate flow.

Download Link to the Sample App: https://github.com/ashiqf/powerplatform/blob/main/OpenAI-SpeechtoText.msapp. Replace the API Key in the Power Automate flow HTTP Action Authorization Header.

OpenAPI Speech to Text API:

The speech to text API provides two endpoints, transcriptions and translations. At present, the maximum file size allowed for uploads is 25 MB and the supported audio formats are mp3, mp4, mpeg, mpga, m4a, wav, and webm. In this blog post, I utilized the Translation API to demonstrate its capability to convert English audio into text, it can understand other languages as well

POST https://api.openai.com/v1/audio/translations

If you have not yet created an API key, please sign up/login for OpenAI and obtain it from there.

Body:

Integration with Power Apps:

I have used a Power Automate flow with the Power Apps trigger to invoke the Speech to Text API via the HTTP connector in Power Automate. Alternatively, you can achieve the same outcome by constructing a Custom Connector. This sample app can be downloaded from this github link.

Microphone Control:

The audio control captures audio input through the device’s microphone and will be sent to the Power Automate flow for conversion into text using the Whisper API. The audio format of the recording depends on the type of device being used

  • 3gp format for Android.
  • AAC format for iOS.
  • Webm format for web browsers.

I’ve tested this control from the app accessed through the web browser. If you encounter an unsupported audio format for OpenAI, you can use utilities such as FFMpeg. Additionally, a .Net version of the control is available for download which can be used in Azure Function. John Liu (MVP) has written a sample Azure function that handles the conversion of audio formats using the aforementioned utility.

Step 1: To add a microphone control to the canvas, insert the Microphone control from the command bar. To preview the recorded audio from the Microphone control, add an Audio control

Step 2: Add a button to convert and to trigger the Power Automate flow. Find below the Power FX code

//Generates a JSON Text with the binary of the Audio file or Recorded audio
Set(varJson,JSON(Microphone1.Audio,JSONFormat.IncludeBinaryData));
Set(strB64Audio, Last(Split(varJson, ",")).Value);
Set(strB64AudioContent, Left(strB64Audio, Len(strB64Audio) - 1));
//Extract Audio Format
Set(varAudioFileType,Mid(varJson,Find(":",varJson)+1,Find(";",varJson)-Find(":",varJson)-1));
//Call the Power Automate Flow
Set(audioText,'SpeechtoText-OpenAIWhisper'.Run(strB64AudioContent,varAudioFileType).audiotext);

The Power FX code performs the following task

  • Stores the audio captured by a Microphone control in a variable as JSON data, including binary data.
  • Extracts the base64-encoded audio content from the JSON data using the string manipulation functions Split, Left, Mid.
  • Determines the audio file type by parsing a string variable.
  • Uses the extracted audio content and file type to call the Power Automate flow ‘SpeechtoText-OpenAIWhisper’ to obtain the corresponding text transcription which comes in later section of this post.
  • Assigns the resulting text transcription to a variable named ‘audioText’, this is assigned to a Text Label to display the converted text from the OpenAI Whisper API.

Step 3: Add a Label control to display the converted Text set to the variable audioText

File Upload Control

As of the day I am writing this post there is no file control that can handle all types of files in Power Apps, I have created a custom component utilizing the Attachment control to create a file attachment control. For further details, please refer to blogpost Uploading Files Made Easy: A Guide to Using the Attachment Control in Power Apps to add the control to the app.

Step 1: Add the file attachment control to the app from the component library. Set the input property for Maximum Attachments to 1 from the component.

Step 2: To extract the binary content of an audio file, add an Image control to the app. The Image control is capable of working with any type of file to extract its content.

Step 3: Add a Button control to convert the Audio from the uploaded file. Find the PowerFX below

//Generates a JSON Text with the binary of the Audio file using the Image control
Set(varFileContent,JSON(Image1.Image,JSONFormat.IncludeBinaryData));
//Extract Base64 content
Set(varExtractedFileContent,Last(Split(varFileContent,",")).Value);
//Remove the last character " from the string
Set(varExtractedFileContent,Left(varExtractedFileContent,Len(varExtractedFileContent)-1));
//Extract Audio Format
Set(varAudioFileType,Mid(varFileContent,Find(":",varFileContent)+1,Find(";",varFileContent)-Find(":",varFileContent)-1));
//Call the Power Automate Flow
Set(audioText,'SpeechtoText-OpenAIWhisper'.Run(varExtractedFileContent,varAudioFileType).audiotext);

Step 4: Add a Label control to display the converted Text set to the variable audioText

Power Automate Flow

Now, let’s create a Power Automate flow with the Trigger type Power Apps to invoke the OpenAI Whisper API and convert speech to text. Step 1: Add two compose action (input parameters) to receive the audio format and content from either the recorded audio captured by the Microphone control or the uploaded audio file from the file attachment control in the Power Apps

{
  "$content-type": @{outputs('Compose-AudioFormat')},
  "$content": @{triggerBody()['Compose-FileContent_Inputs']}
}

Step 2: Add a HTTP connector to make a request to the Whisper API endpoint. Refer to the blog post How to use form-data and form-urlencoded content type in Power Automate or Logic Apps HTTP action for handling multipart/form-data in the HTTP action

Request Body:

{
  "$content-type": "multipart/form-data",
  "$multipart": [
    {
      "headers": {
        "Content-Disposition": "form-data; name=\"model\""
      },
      "body": "whisper-1"
    },
    {
      "headers": {
        "Content-Disposition": "form-data; name=\"file\";filename=\"audiofile.webm\""
      },
      "body": @{outputs('Compose-FileContent')}
    }
  ]
}

Step 3: Add the Respond to a PowerApp or a flow action to pass the converted text back to the app. To get the converted text, use the following expression

body('HTTP-CallaOpenApiModel')['Text']

The expression was constructed based on the response of the Whisper API call. In the event that the response property changes in the future, please ensure to update the expression accordingly.

Summary:

In this post, I’ve outlined a step-by-step guide on how to develop a basic app with Speech to Text functionality using Power Apps and a Power Automate flow leveraging the OpenAI’s Whisper API. The possibilities for using this technology are endless, from creating virtual assistants to generating audio captions and translations. Furthermore, the Whisper API can also be used to transcribe video files, adding even more versatility to its capabilities. It’s worth noting that while Azure offers its own Speech to Text service, it currently does not rely on the OpenAI Whisper Model. However, it’s possible that the two services will eventually integrate in the future. Hope you have found this informational & thanks for reading. If you are visiting my blog for the first time, please do look at my other blogposts.

Do you like this article?

Subscribe to my blog with your email address using the widget on the right side or on the bottom of this page to have new articles sent directly to your inbox the moment I publish them.

How to copy an existing DLP Policy in Power Platform

DLP policies are essential in ensuring that data is managed uniformly across an organization, thereby preventing critical business data from being accidentally published to social media or other connectors. These policies can be created at both the tenant and environment levels, with management handled through the Power Platform admin center. However, it is currently not possible to copy an existing DLP policy from the Admin center. This limitation can create difficulties when there is a need to create new policies based on an existing one.

In this blog post, we will explore various options for copying existing DLP policies to streamline the process. By using these options, you can save time and effort when creating new policies based on existing ones.

  • Power Automate Flow
  • DLP Editor Power Apps from CoE starter kit app
  • Power Shell

Note: To create a DLP policy at the Tenant level, you must be a Power Platform or Global Administrator role in AD.

Power Automate Flow:

The Power Platform Connector for Admins, available in both Power Automate and Power Apps, offers a range of environment lifecycle management capabilities, including DLP policy management.

To copy an existing DLP Policy, we will be utilizing the action List DLP Policies and Create DLP Policy in a Button Flow

Step 1: In the trigger, create two parameters to get the input for the existing Policy Name and the New DLP Policy name followed with the action List DLP Policies from the connector Power Platform for Admins to list all the policies in the Organization

Step 2: To select the DLP policy that you want to copy in a Power Automate flow, add a Filter Array action. This action filters the DLP policies obtained from the List DLP Policies action based on a condition. Specifically, it checks whether the displayName of the DLP Policy from the DLP Policies list action matching with the trigger input Existing DLP Policy Name. Once the Filter Array action is executed, it returns a new array containing only the DLP policy that meets the condition. This filtered array can then be used as input for creating a New DLP policy

Step 3: Add the action Create DLP Policy from the Power Platform for Admins connector with the first property Display Name from the Trigger input. For the other input parameters for the action, use the expression from Output of the Filter Array action as shown below

body('Filter_array')[0]['defaultConnectorsClassification']
body('Filter_array')[0]['connectorGroups']
body('Filter_array')[0]['environmentType']
body('Filter_array')[0]['environments']

Save the changes to ensure that they are preserved. Once you have saved the flow, you can test it to make sure that it works as intended. I have the flow definition saved in my github if you wanted to take a copy of it.

CoE Starter Kit App:

The Center of Excellence (CoE) starter kit core components solution includes a Canvas app DLP Editor with a range of useful features to manage and administer DLP policies. One such feature is the ability to copy an existing Data Loss Prevention (DLP) policy, making it easy to replicate policies across multiple environments or tenants.

This app uses the Power Platform for Admins connector.

Power Shell:

Power Apps Administration PowerShell provides a convenient set of cmdlets that enable you to easily create and manage Data Loss Prevention (DLP) Policies. Microsoft has provided a helpful sample script that allows you to manage your tenant and environment policies. With this script, you can perform a wide range of tasks related to DLP policies, including creating new policies, reading existing policies, updating policies, and removing policies. The sample can be found here. By breaking down the sample script into manageable sections, you can gain a deeper understanding of how DLP policies work and how you can modify them to suit your organization’s needs with PowerShell.

Summary:

This blog post provides a overview of different methods that can be used to copy existing Data Loss Prevention (DLP) policies, which is currently not available from the Power Platform admin center. These techniques can help automate the DLP policy creation process, saving time and effort.

Do you like this article?

Subscribe to my blog with your email address using the widget on the right side or on the bottom of this page to have new articles sent directly to your inbox the moment I publish them.

Uploading Files Made Easy: A Guide to Using the Attachment Control in Power Apps

The Attachment control in Power Apps is a useful feature that allows users to upload and delete files, but it can only be used with data sources such as SharePoint List or Dataverse table. However, if you need to upload and delete files without using these data sources, you can create a custom component using the Attachment control or you can directly use this control in the app. I have followed the tip from Shane Young in this YouTube video to add the Attachment control to a component library.

By creating a custom component Library for the attachment control, you can upload and delete files similar to a Picture control but with the ability to handle any file type across any apps within an environment. This blog post is not a tutorial on how to create the component, but rather

  • How to use it
  • To Save the file in SharePoint Document Library using Power Automate Flow
  • How to customize the component to fit your needs.

How to use it – Add the Component to the Power Apps:

To incorporate this component into your app, you need to first import it into your environment. Please find below the steps to follow

Step 1: Download the component library from my github repo.

Step 2: Create a Blank Canvas App with a temporary name, on the studio command bar, click on the ellipsis > Click ‘Open’, browse to select the downloaded .msapp package. Save the App and then publish it. You would now be able to see the component from the Component Libraries.

Step 3: After following the instructions outlined in this documentation to import the Published component into your app, the component will be available for use in any app within the environment as shown below.

Step 4: Modify the input parameters of the component to adjust settings such as maximum number of attachments, border colour, attachment size, and other defined parameters of the component.

Step 5: To display the uploaded file content within the app or to send the file to a Power Automate flow, you can incorporate any of the following controls based on the file type:

In the Media Property of the control, the formula to display the file content is

First(FileAttachment_1.Attachments.FileAttachment).Value

The file content will be uploaded to the app as binary data with the URL appres://blobmanager/ for each file uploaded from the attachment control. To get the file Name:

First(FileAttachment_1.Attachments.FileAttachment).Name

Note: In the above screenshot, I have set the Max Attachments Component property to 1 in the Step 4

Send the File to Power Automate:

In order to send or store a file using a Power Automate flow, I needed to convert the file content to Base64 format. To accomplish this, I used a image control to capture the file content in binary format. Here is how I configured the image control:

This control works with any types of files to get the binary content.

After obtaining the binary content of the file using the JSON function, I performed some string manipulations to extract the binary content while excluding the Content-Type. Specifically, I used a combination of Split(), Left() and Last() functions to separate the content into an variable varExtractedFileContent.

Set(varFileContent,JSON(Image2.Image, JSONFormat.IncludeBinaryData));
Set(varExtractedFileContent, Last(Split(varFileContent, ",")).Value);
Set(varExtractedFileContent, Left(varExtractedFileContent, Len(varExtractedFileContent) - 1));

By performing these manipulations, I was able to extract the binary content of the file in a format that could be easily passed to a Power Automate flow or other API or action.

This allowed me to send the file to a Power Automate flow, which could then save the file in a SharePoint library or call some other API or action that required the data to be in Base64 format.

The Power Automate flow used to save the file to a SharePoint Document Library is simple. The flow consists of a Power Apps trigger and a SharePoint action Create File, which takes two input parameters: File Name and File Content.

I have used the base64toBinary() expression to convert the base64-encoded string to binary data. This expression is a prerequisite for the SharePoint create file action and ensures that the file is saved correctly to the SharePoint Document Library.

PowerFx to call the flow from Power Apps:

ProcessAttachments.Run(First(AttachmentComponent_1.Attachments.FileAttachment).Name,varExtractedFileContent);

If you need to upload multiple files to a library using the Attachment control, you can use Gallery control with the Image control, Collections, ForAll function, and the OnAddFile property from the Attachment control. First, create a collection to store the files that are uploaded using the Attachment control using the OnAddFile property. Then, use the Gallery control to load the binary of the uploaded files in the Image control. Next, use the ForAll function to iterate through each file in the gallery and call the Power Automate flow on a button click.

Customizing the Component:

The component I’ve created is a simple one for handling file attachments, but it does not have all the properties from the Attachment control. If you need more customization, you can easily modify it to suit your specific needs by adding additional input or output properties.

To add a new property, you can simply edit the component code and include the new property as an input or output parameter.

By customizing the component in this way, you can tailor it to your specific requirements and ensure that it meets all of your file attachment needs

Summary:

In summary, the Attachment control in Power Apps is a useful feature for uploading and deleting files, but it is limited to certain data sources. To work around this limitation, you can create a custom component using the Attachment control, which allows you to handle any file type and bypass the use of data sources like SharePoint or Dataverse tables. Hope you have found this informational & thanks for reading. If you are visiting my blog for the first time, please do look at my other blogposts.

Do you like this article?

Subscribe to my blog with your email address using the widget on the right side or on the bottom of this page to have new articles sent directly to your inbox the moment I publish them.