Resources

DocLLM: A Layout-Aware Generative Language Model for Multimodal Document Understanding (Wang et al., 2023)

Everything you need to know about Voice AI Agents

What multimodal AI really looks like in practice

A Guide to Respectful API Back-Off Strategies

Auto-Playback Across Devices (especially iOS)

AI Tools Every Startup Should Be Using

Join Deepgram at NVIDIA GTC 2024

Three more incredible AI Products to check out!

Introducing Deepgram Aura: Lightning Fast Text-to-Speech for Voice AI Agents

Building an LLM Stack Part 3: The art and magic of Fine-tuning

Deepgram's Startup Program: Accelerating Growth

Uncovering Voicebots: Secrets to building voice AI agents

Predicting the Stock Market & Improving Healthcare: The Power of Sentiment Analysis

Exposing AI-generated videos: Technological secrets revealed

The Future of Healthcare: Enhancing Patient Experience with Voice-Enabled AI Copilots

Everything you need to know about voice cloning

Building an LLM Stack Part 2: Pre-training Tips & Data Processing Tricks

Introducing New Audio Intelligence Models for Sentiment, Intent, and Topic Detection

Lone Wolf vs Community: The Benefits of Open Source Software

Sentiment Analysis Deep-Dive: Teaching Machines about Emotions

Developing an Artificially Intelligent Voice: A Brief History of Text-to-Speech

Top 11 Text-to-Speech AI models of 2025

Building an LLM Stack, Part 1: Implementing Encoders and Decoders

Top 4 Text-to-Speech Uses in Entertainment & Media: When AI blends in

Listening to Forests with Machine Learning & Algorithms

Child-to-Adult Voice Style Transfer: A Case Study in Auditory AI

AI in plain sight: IVR Systems and their hidden complexities

Does Closed-Source AI Perform Better than Open-Source? A Case-Study and Evaluation

Masterclass in Prompt Engineering: A Directory

Challenging LLMs: An in-depth look at Text-to-Speech AI