Newsletter #38: Apply LLMs To Voice Data

Hey 👋, this weekly update contains the latest info on our new product features, tutorials, and our community.

Use Large Language Models With Voice Data

Get more from your voice data with our new guides on using Large Language Models (LLMs) with LeMUR. Learn how to ask questions, summarize, extract, and generate content from your audio data:

Ask questions about your audio data: Learn how to use LeMUR to ask questions and get insightful answers about your audio data.
Summarize audio data: Discover how to quickly summarize your audio data with key takeaways using LeMUR.
Extract and generate data: Find out how to extract tags and descriptions from your audio to enhance metadata and searchability with LeMUR.
Generate content based on audio data: Learn how to create long-form or short-form written content from your audio data using LeMUR.

Fresh From Our Blog

Node.js Speech-to-Text with Punctuation, Casing, and Formatting: Learn how to transcribe audio and video files into text that contains punctuation, casing, and formatting using the AssemblyAI JavaScript SDK. Read more>>

Filter profanity from audio files using Node.js: Filter profanity from audio files using Node.js and the AssemblyAI's Speech-to-text API. Read more>>

Content moderation on audio files with Python: Use AssemblyAI's API to automatically detect sensitive topics in speech data for content moderation. Read more>>

Real-time Speech To Text In Java - Transcribe From Microphone: Transcribe real-time speech to text in Java with audio that is streaming directly from microphone.

How to use @postman to test LLMs with audio data (Transcribe and Understand): Learn how to transcribe audio and video files using AssemblyAI and also how to use LeMUR, AssemblyAI's framework for using Large Language Models on spoken data without having to code at all.

Build A Talking AI with LLAMA 3 (Python tutorial): This tutorial shows you how to build a talking AI using real-time transcription with AssemblyAI, using LLAMA 3 as the language model with Ollama, and ElevenLabs for text-to-speech.