Speech to Text to Document AI in Power Platform
Power Platform
Mar 27, 2023 5:00 PM

Speech to Text to Document AI in Power Platform

by HubSite 365 about Reza Dorrani

Principal Program Manager at Microsoft Power CAT Team | Power Platform Content Creator

External YouTube Channel
Citizen Developer

Power SelectionPower PlatformM365 Hot News

In this step-by-step tutorial, learn how you can convert audio (Power Apps microphone control) or recorded speech or voices (audio files) into text using OpenAI

In this step-by-step tutorial, learn how you can convert audio (Power Apps microphone control) or recorded speech or voices (audio files) into text using OpenAI’s Whisper AI, leverage the new AI Builder Create Text from GPT prebuilt model to generate document content from topic & use the power of connectors in Power Platform to create PDF document. Video showcases how to convert speech to text & then to a PDF document.

Whisper AI can transcribe and translate speech to text.

Azure OpenAI service GPT can create text from instructions. We will leverage the create blog post GPT AI feature to generate the document content.

Create text, answer questions, summarize documents and more with GPT

This model runs on Azure OpenAI Service and can be used for many tasks that involve creating text. Try a template to see how to use generative AI in a variety of scenarios. You can also try writing instructions from scratch. When you’re done, you can use the model in an app or a flow.

PowerApps/whisperswagger.json at master · rdorrani/PowerApps · GitHub

Table of Contents:

  • 00:00 - Introduction to Speech to Text to PDF Document AI in Power Platform
  • 00:42 - Speech to Text Whisper API
  • 01:07 - How to leverage Speech to Text API in Power Apps
  • 03:00 - Use speech to text transcription in PowerApps
  • 05:47 - Introducing new Azure OpenAI Service Create text from GPT action in AI Builder
  • 06:15 - Create Power Automate flow to generate PDF document from GPT AI content
  • 09:40 - Invoke speech to text AI and then GPT AI to create content from App
  • 10:40 - Speech to text to PDF document demo
  • 11:19 - Audio file to text to document with AI demo
  • 11:59 - Speech to Text to Image using DALL.E API demo
  • 12:22 - Subscribe to Reza Dorrani channel