AI Solution

Simplify Transcriptions with OCI Generative AI and OCI Speech

Introduction

If you’ve ever needed to take an audio recording, transcribe it, and summarize what was said, you know how many steps that can take while juggling several files. Let’s use AI to more efficiently solve the problem.

With Oracle Cloud Infrastructure (OCI) Speech and OCI Generative AI, we can automate audio-to-text conversion and build a concise summary all at once. This could, for example, be applied to a call center that handles thousands of calls, using a summary of the call transcripts to draw insights for improving customer experience.

OCI Speech is an AI service that uses automatic speech recognition technology to transform audio-based content into text. OCI Generative AI analyzes this text and can generate, summarize, transform, and extract information from it. You could even take the next step to use these AI capabilities to build a low-code application with Oracle Visual Builder.

Try this project to invoke the OCI Speech REST API, convert audio files into text, and invoke the Generative AI REST API to summarize it.

Demo

Demo: Simplify Transcriptions with OCI Generative AI and OCI Speech (1:44)

Prerequisites and setup

  1. Oracle Cloud account—sign-up page
  2. Visual Builder—documentation for Visual Builder
  3. OCI Speech—documentation for OCI Speech
  4. Integration workflow—Oracle Integration 3
  5. OCI Generative AI—Python SDK

注:为免疑义,本网页所用以下术语专指以下含义:

  1. Oracle专指Oracle境外公司而非甲骨文中国。
  2. 相关Cloud或云术语均指代Oracle境外公司提供的云技术或其解决方案。