Infineon’s DEEPCRAFT AI Suite Accelerates Edge AI Innovation on PSOC Edge MCUs
October 24, 2025
News
Munich, Germany. Infineon Technologies is expanding its Edge AI portfolio with its DEEPCRAFT AI Suite, a comprehensive set of software, tools, and solutions that aid customers with seamless integration of AI into their products.
“With the introduction of our DEEPCRAFT AI Suite, we are further expanding Infineon’s Edge AI software ecosystem for unlocking the full potential of Edge AI,” says Steve Tateosian, SVP and General Manager, IoT, Consumer, and Industrial MCUs at Infineon.
DEEPCRAFT is optimized for Infineon’s PSOC Edge microcontrollers allowing engineers the ability to fully leverage Infineon’s Edge AI ecosystem including performance on demand, energy-efficient design, and system-level optimization.
Edge AI Ecosystem
Solutions are available through Infineon's centralized DEEPCRAFT AI Hub and ModusToolbox, allowing the contribution of models or easily adopt ready-to-use ones. According to the press release, the ecosystem is designed to reduce friction from model development to integration into commercial products.
DEEPCRAFT AI Hub:
The DEEPCRAFT AI Hub provides access to more than 50 content resources, including open-source models, Infineon software, tools, and solutions, as well as case studies from industrial, consumer, and automotive applications.
DEEPCRAFT Studio:
DEEPCRAFT Studio supports audio, radar and other time-series data, now it adds support for computer vision. DEEPCRAFT Studio is an end-to-end platform for the design of robust AI and machine learning models for the edge. It creates enhanced models that are ready for use in commercial products and is free to use with Infineon hardware.
DEEPCRAFT Model Converter:
Engineers can utilize the DEEPCRAFT Model Converter to enhance both proprietary and open-source models to run on Infineon hardware. The converter supports popular AI frameworks, including PyTorch, TFLite, and Keras, aiding seamless execution on PSOC Edge and PSOC 6 MCUs.
PSOC Edge MCUs:
The PSOC Edge family of Arm Cortex-M microcontrollers deliver high-performance, low-power, and secured hardware with machine learning acceleration. Additionally, the devices provide advanced security features such as Infineon Edge Protect Category 4 (EPC4) with PSA Certified L2 and L4 iSE, PCI pre-certification, and a secure enclave to protect designs from concept through manufacturing. A 2.5D GPU facilitates responsive, high-quality graphical interfaces at the edge, offering accurate visuals at a fraction of the performance and energy cost of traditional 3D processors. PSOC Edge is fully supported by ModusToolbox, Zephyr, and DEEPCRAFT AI Suite.
Voice-Controlled Product Development on PSOC Edge
Developers can use DEEPCRAFT Voice & Audio Solutions for the design of high-quality, voice-controlled products. It enhances speech intelligibility by removing unwanted noise, while DEEPCRAFT Voice Assistant supports natural voice interfaces running locally on edge devices.
Because they are ready for the PSOC Edge architecture, both are suitable for dual-core Cortex-M55 with Ethos-U55 up to 400 MHz and Cortex-M33 + NNLite cores with up to 200 MHz. On PSOC Edge, the Voice & Audio Solutions achieve always-on listening below 1mW with very low latency room conditions, avoiding repeated wake-word prompts and extending battery runtime.
Infineon states that PSOC Edge delivers up to 75 percent faster audio processing at roughly half the energy consumption of competing solutions, which further extends device performance and battery life. Combining its AI acceleration and its advanced memory architecture makes it possible to run multi-megabyte models, such as Voice ID.
Utilizing these abilities allows developers to integrate powerful, energy-efficient voice and audio intelligence directly into their products, accelerating development and bringing smart edge-enabled products to market faster.
“Our Edge AI approach is designed to provide a comprehensive set of hardware and software solutions, including the DEEPCRAFT AI Suite, which includes our AI Hub with Ready Models and audio tuning tools. As partner of choice for Edge AI, we offer advanced products and solutions for the easy implementation of AI/ML capabilities in the next generation of IoT edge devices. This enables our customers to develop their models from scratch or integrate off-the-shelf models and solutions into their products, thereby shortening time-to-market,” ends Tateosian.
For more information on DEEPCRAFT AI Suite, visit infineon.com/design-resources/embedded-software/deepcraft-edge-ai-solutions.
For more information about PSOC Edge, visit infineon.com/promo/next-generation-mcu.
