
Granite-speech-3.3-8b is a compact and efficient speech-language model, specifically designed for automatic speech recognition (ASR) and automatic speech translation (AST).
Quick readCRAISEE · Apr 25, 2026reference
Try it on CRAISEE nowGo create

Granite-speech-3.3-8b is a compact and efficient speech-language model, specifically designed for automatic speech recognition (ASR) and automatic speech translation (AST).
Enables precise control of character actions and expressions from a reference image.

State of the art video generation model. Veo 2 can faithfully follow simple and complex instructions, and convincingly simulates real-world physics as well as a wide range of visual styles.

Bria Increase resolution upscales the resolution of any image. It increases resolution using a dedicated upscaling method that preserves the original image content without regeneration.

An AI system that can create realistic images and art from a description in natural language.