Technological Projects

The engine behind next-generation multimedia AI

Combine rendering, video processing and AI inference into a single heterogeneous execution pipeline optimized for modern CPUs and GPUs.

Talk to an expert!

VALUE PROPOSITION

We ensure exclusive solutions to keep power under control

FLEXIBILITY AND CUSTOMIZATION

We tailor the engine to client needs, optimizing performance, accuracy, and speed based on project and hardware requirements.

continuous innovation

Our in-house engine allows us to stay ahead of AI and video processing trends, delivering cutting-edge solutions.

SUPPORT AND MAINTENANCE

As the engine’s developers, we offer specialized support and rapid, customized maintenance when needed.

FLEXIBILITY AND CUSTOMIZATION

We tailor the engine to client needs, optimizing performance, accuracy, and speed based on project and hardware requirements.

continuous innovation

Our in-house engine allows us to stay ahead of AI and video processing trends, delivering cutting-edge solutions.

SUPPORT AND MAINTENANCE

As the engine’s developers, we offer specialized support and rapid, customized maintenance when needed.

FEATURES

Our experience in your hands: Time to empower your multimedia projects with Fluendo AI Engine

Versatile integration

Fluendo AI Engine integrates with multiple APIs and programming languages, easily incorporating it into existing workflows and systems. This flexibility allows businesses to adopt this technology without overhauling their current infrastructure.

With bindings available for C++, Python, and C# and integration with GStreamer, clients can easily embed Fluendo AI Engine into their existing codebases, eliminating the need for significant application changes. This ensures a smooth and efficient integration process, minimizing disruption while maximizing the technology’s value.

Versatile integration

Integration with GStreamer

If your application is based on GStreamer, the AI Engine offers an optional module for direct integration with your GStreamer pipeline. If desired, we can develop self-contained GStreamer plugins to perform your AI tasks fully isolatedly.

Integration with GStreamer

Truly cross-platform

With AI Engine, the client code is written once and compiled without changes across multiple hardware environments and operating systems. It automatically selects the best available hardware on the machine, whether it’s AMD, Intel, or NVIDIA GPUs, ensuring an optimal workflow pipeline. Additionally, our engine supports video from multiple graphic APIs, such as DirectX12 and Vulkan, allowing for more efficient operation across a wide range of applications and systems.

// Inputs setting
fsai::Image image(file);
auto engine = fsai::EngineFactory::createByType("dml");
auto texture = engine->createTexture(image);

// Specific API setting
fsai::sports::strongsort::ModelDetectionFastGeneric model{“models”};
fsai::sports::strongsort::DetectorFastGeneric detector{modelGeneric, engine};

// Inference
auto detections = detector.push(texture);

// Get bounding boxes
for (auto& detection : detection){
   const auto& coords = detection.getBoundingBox() ; }

// Inputs setting
var image = Fsai.Image(file);
var engine = new Fsai.EngineFactory.CreateByType("dml");
var texture = engine.CreateTexture(image);

// Specific API setting
var model = Fsai.Sports.Strongsort.ModelDetectionFastGeneric(“models”);
var detector  =  Fsai.Sports.Strongsort.DetectorFastGeneric(model, engine);

// Inference
auto detections = detector.Push(texture);

// Get bounding boxes
foreach (Fsai.Sports.Strongsort.Object detection in detections){
   var coords = detection.GetBoundingBox();}

## Inputs setting

image = fsai.Image(file);
engine = fsai.Engine_factory.create_by_type("dml")
texture = engine.Create_texture(image)

## Specific API setting
model = fsai.sports.strongsort.model_detection_fast_generic(“models”)
detector  =  fsai.sports.strongsort.detector_fast_generic(model, engine)

## Inference
detections = detector.push(texture)

## Get bounding boxes
for detection in detections: 
coords = detection.get_bounding_box()

Bits & Bytes

Explore our blog, one byte at a time. Our team unpack our latest news, industry insights and in-depth articles to connect you with the multimedia world.

Blog

Read more about our work

View All

October 20, 2026

Advancing RAVEN: Fluendo wins Red.es AI grant

multimedia-edge-ai, the-lab, fluendo-ai-plugins, raven

Driving the future of multimedia innovation We are proud to announce that Fluendo has been selected as a recipient of a grant Red.es IA cadena de valor 2025 Call for Proposals for R&D in Artificial Intelligence (C003/25-ED), framed within the Digital Spain 2026 Agenda. This achievement underscores our commitment to pushing the boundaries of multimedia technology and supports our long-term R&D roadmap. This boost will allow us to take our prototype, RAVEN, to the next level through the RAVEN HOOD project, transforming it into a real-time, cross-platform, open-source AI multimedia engine designed to integrate with the most demanding value chains.

September 3, 2026

Raven AI Engine v0.4.7: From an AI inference engine to a heterogeneous GPU computing platform

broadcasting, video-surveillance, multimedia-edge-ai, gstreamer, fluendo-ai-plugins, anonymizer, raven

Raven v0.4.7 and FAIP v1.2.6 extend GPU-accelerated AI processing to Ubuntu x64 with CUDA, Vulkan, heterogeneous execution, and user-defined shaders.

April 30, 2024

Non-assisted scene calibration: an innovative impact on sports analysis

sports, multimedia-edge-ai, raven

Autonomous scene calibration for enhanced sports video analysis.

April 24, 2024

Assisted scene calibration for sports analysis

sports, multimedia-edge-ai, raven

Evolution of sports analysis with AI and computer vision.