Silent AI is OVER! Unmute by Kyutai Makes LLMs Speak & Listen

The world of Artificial Intelligence is buzzing with exciting news, and at the forefront is Unmute by Kyutai. This groundbreaking technology is set to transform how we interact with Large Language Models (LLMs), making them truly conversational by empowering them to listen and speak. If you’ve ever wished your favorite text-based AI could engage in a […]

Meet Parakeet TDT 0.6B V2: NVIDIA’s New ASR Champion Which is Better than Whisper3

The world of Automatic Speech Recognition (ASR) is constantly evolving. Accuracy, speed, and efficiency are paramount. NVIDIA has just raised the bar significantly with its latest release: the Parakeet TDT 0.6B V2 model. This new English ASR model isn’t just an incremental update. It’s a powerhouse that has already topped the Hugging Face Open ASR Leaderboard. Remarkably, […]

IBM Granite 3.3 Unveiled: Advancing AI Speech, Reasoning, and RAG

IBM continues to push the boundaries of enterprise-focused artificial intelligence with its latest release: IBM Granite 3.3. This significant update expands the Granite family’s capabilities, introducing powerful new features for speech processing, refining reasoning abilities, and offering innovative tools to enhance retrieval-augmented generation (RAG). Staying true to IBM’s commitment, all Granite 3.3 models and tools are […]

Qwen2-Audio by Alibaba Transforms What You Say into Written Words

Alibaba’s Qwen research team recently introduced their latest creation, Qwen2-Audio, an upgraded version of their original Qwen-Audio model that was introduced last year. The model aims to strengthen human-AI communication by understanding speech and audio. Let’s explore the key capabilities of this new AI system! What is Qwen2-Audio Qwen2-Audio is a Large Audio-Language Model (LALM) […]