LeMUR

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.

All LeMUR Cookbooks

Basic LeMUR Workflows

Process Audio Files with LLMs Using LeMUR
Use LeMUR Specialized Endpoints
🆕 Receive AI coaching from LeMUR’s Task Endpoint
🆕 Generate Action Items using LeMUR’s Task Endpoint
🆕 Ask questions about a transcript using LeMUR’s Task Endpoint
Calculating LeMUR Costs by Counting Input Tokens

Analyze Speakers with LeMUR

Processing Speaker Labels with LeMUR’s Custom Text Input Parameter
Use LeMUR for Speaker Identification

Get Quotes and Citations with LeMUR

Extract Dialogue Data with LeMUR and JSON
Extract Citations from a Transcript with Semantic Search
Extract Quotes from a Transcript with LeMUR’s Custom Text Input Parameter
🆕 Create Transcript Citations using OpenAI embeddings

Substitute Audio Intelligence with LeMUR

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

Use Case Specific LeMUR Workflows

Implement a Sales Playbook Using LeMUR
How to Pass Context from Previous LeMUR Requests
Generate Action Items from a Meeting with LeMUR
Phone Call Segmentation Using LeMUR
🆕 SOAP Note Generation