Overview

Apply Large Language Models to spoken data. A Large Language Model (LLM) is a machine learning model that uses natural language processing (NLP) to generate text. LeMUR is a framework that lets you apply LLMs to audio transcripts, for example to ask questions about a call, or to summarize a meeting.

Basic LeMUR Workflows

• Setup an AI Coach with LeMUR

• Generate Action Items with LeMUR

• Prompt A Structured Q&A Response Using LeMUR

• Estimate Input Token Costs for LeMUR

Analyze Speakers with LeMUR

• Process Speaker Labels with LeMURs Custom Text Input Parameter

• Identify Speaker Names From the Transcript Using LeMUR

Get Quotes and Citations with LeMUR

• Extract Dialogue Data with LeMUR and JSON

• Extract Quotes with Timestamps Using LeMUR + Semantic Search

• Extract Transcript Quotes with LeMURs Custom Text Input Parameter

• Generate Transcript Citations using LeMUR

Substitute Audio Intelligence with LeMUR

Model/Feature	Use with LeMUR
Sentiment Analysis	Customer Call Sentiment Analysis
Custom Vocabulary	Boost Transcription Accuracy
Auto Chapters	Creating Chapter Summaries with the Custom Text Input Parameter
Summarization	Create Custom Summaries using the Task Endpoint
Topic Detection	Create Custom Topic Tags

Use Case-Specific LeMUR Workflows

• Implement a Sales Playbook Using LeMUR

• Pass Context from Previous LeMUR Requests

• Generate meeting action items with LeMUR

• Segment A Phone Call using LeMUR

• Generate SOAP Notes using LeMUR