How to Convert Speech to Text from Canvas PowerApps (Part III Microsoft Flow)

Introduction:

In this blog we will see how to Configure Microsoft flows for Converting Speech to Text

Lets see this in 3 Different Blogs, Here we start with Microsoft Azure

 

Pre-Requisites :

 

• Canvas PowerApps
• Microsoft Azure
• Microsoft Flow

 

1. Navigate to https://make.powerautomate.com

 

2. Select New --> Select Instant Cloud Flow

 

3. Add Step --> Initialize Variable

 

 

Add Value as ASK FROM POWERAPPS

4. Add Another Variable

 

 

replace(variables('Data'),'data:audio/webm;base64,','')

 

5. Add Compose to Convert to JSON

 

 

json(variables('ReplaceValues'))

 

6. Now Add Parse JSON and Pass input from COMPSE

 

 

 

{
    "type": "object",
    "properties": {
        "Url": {
            "type": "string"
        }
    }
}

 

7. Get the Value from JSON and Pass value as URL

 

 

8. Trigger a HTTP Request to Function app (URL : Function APP URL)

 

 

9. Trigger HTTP Request for Cognitive Service with KEY and Content Type

 

 

Here the URL will be Your Cognitive URL and Key as Cognitive Key

 

10. Parse JSON and the Input from Point 9

 

 

 

{
    "type": "object",
    "properties": {
        "RecognitionStatus": {
            "type": "string"
        },
        "Offset": {
            "type": "integer"
        },
        "Duration": {
            "type": "integer"
        },
        "NBest": {
            "type": "array",
            "items": {
                "type": "object",
                "properties": {
                    "Confidence": {
                        "type": "number"
                    },
                    "Lexical": {
                        "type": "string"
                    },
                    "ITN": {
                        "type": "string"
                    },
                    "MaskedITN": {
                        "type": "string"
                    },
                    "Display": {
                        "type": "string"
                    }
                },
                "required": [
                    "Confidence",
                    "Lexical",
                    "ITN",
                    "MaskedITN",
                    "Display"
                ]
            }
        },
        "DisplayText": {
            "type": "string"
        }
    }
}

 

10. At last Respond to PowerApps

 

 

 

That's it 

 

How to Convert Speech to Text from Canvas PowerApps (Part II Azure)

Introduction:

In this blog we will see how to Configure Microsoft Azure for Converting Speech to Text

Lets see this in 3 Different Blogs, Here we start with Microsoft Azure

 

Pre-Requisites :

 

• Canvas PowerApps
• Microsoft Azure
• Microsoft Flow

 

1. Navigate to https://portal.azure.com

 

2. Click Search and Search for Resource Group

 

 

3. Input the Resource Group name and Click Review and Create

 

4. Once the Resource Group is Created then Click On Search at the Top and Search for FUNCTION APP

 

5. Now Create a New Function App like below Image

 

 

6. Now Click Review and Create

 

7. Once Function App Created Open the Function App and Search for Functions --> Select Create --> Select HTTP Trigger --> Select New Function and Click Create

 

 

8. Once the Function App is Created, In the Function App Search Search for Advance Tools  and Click GO

 

9. It will Open a POP-UP Click DEBUG and Select CMD

 

10. Once Page Loaded Click Site Folder --> wwwroot

 

  

 

11. Once the WWWROOT Loaded Select NEW and Select New Folder

 

 

 

12. Name it as "webm-to-wave"

 

13. Now go this Link and Select Windows and Download the File

 

14. Once the File is Downloaded Extract the File and GO to BIN and You can see Below Three Files

 

 

15. Drag and Drop it to the Folder which we Created

 

16. Once the File is Uploaded Go one Step Back there you can See the AZURE FUNCTION WHICH YOU CREATED

 

17. Open that and Click New and Create a File function.json / readme.md / run.csx

 

18. Here is my GITHUB link you can see the Files which need to be available in function.json/readme.md and run.csx 

 

19. Once Done Click Save.

 

20. Now Again Navigate to https://portal.azure.com

 

21. Search for Speech Services

 

 

 

22. Create a new Speech Services like below and Click Review and Create 

 

23. Once the Speech Service is Created Open it and Select KEYS and ENDPOINT

 

24. Copy the KEY and ENDPOINT

 

 

That's it For Azure 

 

In Next Blog, we will see how to Write Microsoft Flow to Achieve Speech to Text

How to Convert Speech to Text from Canvas PowerApps (Part I Canvas App)

Introduction:

In this Blog, we will see how to Convert Speech to Text From Canvas PowerApps with Part 1 Canvas Apps

Lets see this in 3 Different Blogs, First we Start with Canvas PowerApps

 

Pre-Requisites :

 

• Canvas PowerApps
• Microsoft Azure
• Microsoft Flow

 

1. Canvas PowerApps :

 

• Navigate to https://make.powerapps.com
• Click Apps
• Select Canvas App --> Select Phone

• And Click Create
• Select Insert --> Select Microphone

• In the OnStop of the Microphone Input the Below Values

 

 

 

ClearCollect(
    AudioCollection,
    Microphone1.Audio
);
Set(
    JSONValue,
    JSON(
        AudioCollection,
        JSONFormat.IncludeBinaryData
    )
);

 

 

 

Here Microphone1 is name of Microphone media

 

• Now Click Insert and Add Audio

 

• Select Audio And Click Media and Paste the Below Code

 

 

 

Microphone1.Audio

 

 

 

This Code Uses when ever you tired to Record By Speech you can hear Back from AUDIO option by Playing

 

•  Now Add a Button and Name it as SUBMIT (or) Convert to Text
•  Select Power Automate at the Left Side of the Tab and Click Add New Flow

• You will see in Next Blog How to Create a MICROSOFT FLOWS in Next Blog