Skip to main content

Notifications

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

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

 

Pre-Requisites :

 

 

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

 

2. Select New --> Select Instant Cloud Flow

 

3. Add Step --> Initialize Variable

 

rampprakash_0-1679038194550.png

 

Add Value as ASK FROM POWERAPPS

4. Add Another Variable

 

rampprakash_1-1679038220574.png

 

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

 

5. Add Compose to Convert to JSON

 

rampprakash_2-1679038268441.png

 

json(variables('ReplaceValues'))

 

6. Now Add Parse JSON and Pass input from COMPSE

 

rampprakash_3-1679038308430.png

 

 

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

 

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

 

rampprakash_4-1679038361172.png

 

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

 

rampprakash_5-1679038428381.png

 

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

 

rampprakash_6-1679038496948.png

 

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

 

10. Parse JSON and the Input from Point 9

 

rampprakash_7-1679038558575.png

 

 

{
 "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

 

rampprakash_8-1679038591429.png

 

 

That's it 🙂

 

Comments

*This post is locked for comments

  • SA16 Profile Picture SA16
    Posted at
    How to Convert Speech to Text from Canvas PowerApps (Part III Microsoft Flow)

    Hi All, 

    @fishscience_2  , @rampprakash , @Vijay_Raju , @NeilMayo 

    Where do you get the function app URL in step 8?

    I have a speech service on cognitive services but no function app?

  • NeilMayo Profile Picture NeilMayo
    Posted at
    How to Convert Speech to Text from Canvas PowerApps (Part III Microsoft Flow)

    @fishscience_2  thank you for your response although unfortunately ive already tried that same error 

  • fishscience_2 Profile Picture fishscience_2 53
    Posted at
    How to Convert Speech to Text from Canvas PowerApps (Part III Microsoft Flow)

    @NeilMayo in step 7, try value replace url. It works for me.

  • NeilMayo Profile Picture NeilMayo
    Posted at
    How to Convert Speech to Text from Canvas PowerApps (Part III Microsoft Flow)

    Hi @rampprakash , 

    getting the same error as @fishscience_2 except its in the first http request any solutions or ideas would be greatly appreciated, thank you.

     

    {"title":"ffmpeg version 6.0-full_build-www.gyan.dev Copyright (c) 2000-2023 the FFmpeg developers\r\n built with gcc 12.2.0 (Rev10, Built by MSYS2 project)\r\n configuration: --enable-gpl --enable-version3 --enable-static --disable-w32threads --disable-autodetect --enable-fontconfig --enable-iconv --enable-gnutls --enable-libxml2 --enable-gmp --enable-bzlib --enable-lzma --enable-libsnappy --enable-zlib --enable-librist --enable-libsrt --enable-libssh --enable-libzmq --enable-avisynth --enable-libbluray --enable-libcaca --enable-sdl2 --enable-libaribb24 --enable-libdav1d --enable-libdavs2 --enable-libuavs3d --enable-libzvbi --enable-librav1e --enable-libsvtav1 --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxavs2 --enable-libxvid --enable-libaom --enable-libjxl --enable-libopenjpeg --enable-libvpx --enable-mediafoundation --enable-libass --enable-frei0r --enable-libfreetype --enable-libfribidi --enable-liblensfun --enable-libvidstab --enable-libvmaf --enable-libzimg --enable-amf --enable-cuda-llvm --enable-cuvid --enable-ffnvcodec --enable-nvdec --enable-nvenc --enable-d3d11va --enable-dxva2 --enable-libmfx --enable-libshaderc --enable-vulkan --enable-libplacebo --enable-opencl --enable-libcdio --enable-libgme --enable-libmodplug --enable-libopenmpt --enable-libopencore-amrwb --enable-libmp3lame --enable-libshine --enable-libtheora --enable-libtwolame --enable-libvo-amrwbenc --enable-libilbc --enable-libgsm --enable-libopencore-amrnb --enable-libopus --enable-libspeex --enable-libvorbis --enable-ladspa --enable-libbs2b --enable-libflite --enable-libmysofa --enable-librubberband --enable-libsoxr --enable-chromaprint\r\n libavutil 58. 2.100 / 58. 2.100\r\n libavcodec 60. 3.100 / 60. 3.100\r\n libavformat 60. 3.100 / 60. 3.100\r\n libavdevice 60. 1.100 / 60. 1.100\r\n libavfilter 9. 3.100 / 9. 3.100\r\n libswscale 7. 1.100 / 7. 1.100\r\n libswresample 4. 10.100 / 4. 10.100\r\n libpostproc 57. 1.100 / 57. 1.100\r\n[matroska,webm @ 000001706cbc0b80] Format matroska,webm detected only with low score of 1, misdetection possible!\r\n[matroska,webm @ 000001706cbc0b80] EBML header parsing failed\r\nC:\\local\\Temp\\hckwpyxh.szk.webm: Invalid data found when processing input\r\n","status":400}

  • fishscience_2 Profile Picture fishscience_2 53
    Posted at
    How to Convert Speech to Text from Canvas PowerApps (Part III Microsoft Flow)

    The issue is figured out. You can ignore my question above. Thank you!

  • fishscience_2 Profile Picture fishscience_2 53
    Posted at
    How to Convert Speech to Text from Canvas PowerApps (Part III Microsoft Flow)

    Here is the detailed error message:

    {"title":"ffmpeg version 6.0-full_build-www.gyan.dev Copyright (c) 2000-2023 the FFmpeg developers\r\n built with gcc 12.2.0 (Rev10, Built by MSYS2 project)\r\n configuration: --enable-gpl --enable-version3 --enable-static --disable-w32threads --disable-autodetect --enable-fontconfig --enable-iconv --enable-gnutls --enable-libxml2 --enable-gmp --enable-bzlib --enable-lzma --enable-libsnappy --enable-zlib --enable-librist --enable-libsrt --enable-libssh --enable-libzmq --enable-avisynth --enable-libbluray --enable-libcaca --enable-sdl2 --enable-libaribb24 --enable-libdav1d --enable-libdavs2 --enable-libuavs3d --enable-libzvbi --enable-librav1e --enable-libsvtav1 --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxavs2 --enable-libxvid --enable-libaom --enable-libjxl --enable-libopenjpeg --enable-libvpx --enable-mediafoundation --enable-libass --enable-frei0r --enable-libfreetype --enable-libfribidi --enable-liblensfun --enable-libvidstab --enable-libvmaf --enable-libzimg --enable-amf --enable-cuda-llvm --enable-cuvid --enable-ffnvcodec --enable-nvdec --enable-nvenc --enable-d3d11va --enable-dxva2 --enable-libmfx --enable-libshaderc --enable-vulkan --enable-libplacebo --enable-opencl --enable-libcdio --enable-libgme --enable-libmodplug --enable-libopenmpt --enable-libopencore-amrwb --enable-libmp3lame --enable-libshine --enable-libtheora --enable-libtwolame --enable-libvo-amrwbenc --enable-libilbc --enable-libgsm --enable-libopencore-amrnb --enable-libopus --enable-libspeex --enable-libvorbis --enable-ladspa --enable-libbs2b --enable-libflite --enable-libmysofa --enable-librubberband --enable-libsoxr --enable-chromaprint\r\n libavutil 58. 2.100 / 58. 2.100\r\n libavcodec 60. 3.100 / 60. 3.100\r\n libavformat 60. 3.100 / 60. 3.100\r\n libavdevice 60. 1.100 / 60. 1.100\r\n libavfilter 9. 3.100 / 9. 3.100\r\n libswscale 7. 1.100 / 7. 1.100\r\n libswresample 4. 10.100 / 4. 10.100\r\n libpostproc 57. 1.100 / 57. 1.100\r\n[matroska,webm @ 000001ad56ea1000] Format matroska,webm detected only with low score of 1, misdetection possible!\r\n[matroska,webm @ 000001ad56ea1000] EBML header parsing failed\r\nC:\\local\\Temp\\1v420kse.gva.webm: Invalid data found when processing input\r\n","status":400}

  • fishscience_2 Profile Picture fishscience_2 53
    Posted at
    How to Convert Speech to Text from Canvas PowerApps (Part III Microsoft Flow)

    I build flow as shown below. Skip step7, and add uri from Parse JSON into HTTP directly

    fishscience_2_0-1689586296522.png

    However get error as shown below:

    fishscience_2_1-1689586422375.png

    Can suggest? Really appreciate your answer

  • fishscience_2 Profile Picture fishscience_2 53
    Posted at
    How to Convert Speech to Text from Canvas PowerApps (Part III Microsoft Flow)

    When I built flow, skip step 7, add url into http action directly.

    fishscience_2_0-1689585899581.png

    However get error for HTTP action

    fishscience_2_1-1689585957352.png

    Here is the detailed error message:

    {"title":"ffmpeg version 6.0-full_build-www.gyan.dev Copyright (c) 2000-2023 the FFmpeg developers\r\n built with gcc 12.2.0 (Rev10, Built by MSYS2 project)\r\n configuration: --enable-gpl --enable-version3 --enable-static --disable-w32threads --disable-autodetect --enable-fontconfig --enable-iconv --enable-gnutls --enable-libxml2 --enable-gmp --enable-bzlib --enable-lzma --enable-libsnappy --enable-zlib --enable-librist --enable-libsrt --enable-libssh --enable-libzmq --enable-avisynth --enable-libbluray --enable-libcaca --enable-sdl2 --enable-libaribb24 --enable-libdav1d --enable-libdavs2 --enable-libuavs3d --enable-libzvbi --enable-librav1e --enable-libsvtav1 --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxavs2 --enable-libxvid --enable-libaom --enable-libjxl --enable-libopenjpeg --enable-libvpx --enable-mediafoundation --enable-libass --enable-frei0r --enable-libfreetype --enable-libfribidi --enable-liblensfun --enable-libvidstab --enable-libvmaf --enable-libzimg --enable-amf --enable-cuda-llvm --enable-cuvid --enable-ffnvcodec --enable-nvdec --enable-nvenc --enable-d3d11va --enable-dxva2 --enable-libmfx --enable-libshaderc --enable-vulkan --enable-libplacebo --enable-opencl --enable-libcdio --enable-libgme --enable-libmodplug --enable-libopenmpt --enable-libopencore-amrwb --enable-libmp3lame --enable-libshine --enable-libtheora --enable-libtwolame --enable-libvo-amrwbenc --enable-libilbc --enable-libgsm --enable-libopencore-amrnb --enable-libopus --enable-libspeex --enable-libvorbis --enable-ladspa --enable-libbs2b --enable-libflite --enable-libmysofa --enable-librubberband --enable-libsoxr --enable-chromaprint\r\n libavutil 58. 2.100 / 58. 2.100\r\n libavcodec 60. 3.100 / 60. 3.100\r\n libavformat 60. 3.100 / 60. 3.100\r\n libavdevice 60. 1.100 / 60. 1.100\r\n libavfilter 9. 3.100 / 9. 3.100\r\n libswscale 7. 1.100 / 7. 1.100\r\n libswresample 4. 10.100 / 4. 10.100\r\n libpostproc 57. 1.100 / 57. 1.100\r\n[matroska,webm @ 000001ad56ea1000] Format matroska,webm detected only with low score of 1, misdetection possible!\r\n[matroska,webm @ 000001ad56ea1000] EBML header parsing failed\r\nC:\\local\\Temp\\1v420kse.gva.webm: Invalid data found when processing input\r\n","status":400}

     

    Can you suggest? Really appreciate your help!

  • fishscience_2 Profile Picture fishscience_2 53
    Posted at
    How to Convert Speech to Text from Canvas PowerApps (Part III Microsoft Flow)

    @rampprakash for step 7, what type for "set value from json" variable?

  • Ram Prakash Profile Picture Ram Prakash 5,154
    Posted at
    How to Convert Speech to Text from Canvas PowerApps (Part III Microsoft Flow)

    Hi Once you done this, you can speak directly in Canvas App with Micro Phone and click Submit it will redirect to Flow and it will provide a response