BeagleBone AI-64 SBC features TI TDA4VM Cortex-A72/R5F SoC with 8 TOPS AI accelerator

BeagleBone AI-64

BeagleBone AI-64 is a single board computer (SBC) powered by a Texas Instruments TDA4VM dual-core Cortex-A72 + hexa-core Cortex-R5F processor which also embeds an 8 TOPS AI accelerator, plus three DSP, as well as plenty of I/Os that makes it ideal for advanced AI industrial applications. It follows the BeagleBone-AI SBC launched in 2019, but with much higher specs including a 64-bit Arm processor, 4GB RAM, three USB 3.0 ports, an M.2 E-Key socket with PCIe, USB and SDIO, plus the usual expansion headers that keep compatibility with existing BeagleBone cape add-on boards.   BeagleBone AI-64 specifications compared to BeagleBone-AI and BeagleBone Black boards: Another notable change is that a mini DisplayPort has now replaced the micro HDMI port found in earlier boards. The TDA4VM SoC comes with many co-processors, so it will be interesting to see how well those are supported in the software. provides Debian 11.3 with […]

Beagle-Pi Emulator is a Raspberry Pi HAT adapter for BeagleBone Black (Crowdfunding)

We recently reported the Raspberry Pi boards were getting really expensive due to a lack of supply, and the problem has gone on for while without a clear idea when the issue will be resolved. This does not help Raspberry Pi HAT manufacturers, and for instance, Sequent Microsystems has made Raspberry Pi HATs over the years most models with multiple relays, but also others for temperature sensors, and others automation applications. One solution would be to use compatible boards like ODROID-C4 or Rock64, but Sequent Microsystems found out the BeagleBone Black Industrial was well-stocked by various distributors, and instead, they designed the “Beagle-Pi Emulator” adapter to use Raspberry Pi HAT on the Texas Instruments Sitara AM3358 board.   An adapter is needed because the BeagleBone Black boards are equipped with two 46-pin headers instead of the 40-pin header on Raspberry Pi SBC’s. The expansion board routes I2C, SPI, four serial […]

PicoVoice offline Voice AI engine gets free tier for up to 3 users

PicoVoice offline Voice AI engine has now a free tier that allows people to create custom wake words and voice commands easily for up to three users on any hardware including Raspberry Pi and Arduino boards. I first learned about PicoVoice about a year ago when the offline voice AI engine was showcased on a Raspberry Pi fitted with ReSpeaker 4-mic array to showcase the company’s Porcupine custom wake word engine, and Rhino Speech-to-Intent engine. The demo would support 9 wake words with Alexa, Bumblebee, Computer, Hey Google, Hey Siri, Jarvis, Picovoice, Porcupine, and Terminator. More importantly, the solution allows you to easily create your own custom words in minutes from a web interface by simply typing the selected wake word, with no need for hundreds of voice samples or waiting weeks to get it done. So I tried “Hey You” first, but I was told it was too short, […]

Picovoice Cobra Voice Activity Detection Engine shown to outperform Google WebRTC VAD

Picovoice Cobra Voice Activity Detection (VAD) engine has just been publicly released with support for Raspberry Pi, BeagleBone, NVIDIA Jetson Nano, Linux 64-bit, macOS 64-bit, Windows 64-bit, Android, iOS, and web browsers that support WebAssembly. Support for other Cortex-M and Cortex-A based SoCs can also be made available but only to enterprise customers. Picovoice already offered custom wake word detection with an easy and quick web-based training and offline voice recognition for Raspberry Pi, and even later ported their voice engine to Arduino. Cobra VAD is a new release, and, like other VADs, aims to detect the presence of a human voice within an audio stream. Picovoice Cobra can be found on Github, but note this is not an open-source solution, and instead, dynamic library is provided for various targets, together with header files and demos in C, Python, Rust, and WebAssembly, as well as demo apps for iOS […]

ODYSSEY-X86J4105 SBC Unboxing and Re_Computer Case Review

Seeed Studio ODYSSEY-X86J4105 is an Intel Celeron J4105 Gemini Lake SBC that also happens to integrate an Arduino compatible Microchip SAMD21 Arm Cortex M0+ microcontroller that makes it suitable as an all-in-one Arduino platform. But it can do much more with 8GB RAM, an optional 64GB eMMC flash, HDMI & USB-C DisplayPort 4K video outputs, dual Gigabit Ethernet, and support for both SATA and NVMe storage. The board runs Windows 10 Enterprise by default (if you purchase the board with an eMMC flash), and supports Linux distributions as well. Seeed Studio sent me a review sample, so I’ll start by checking out the hardware first. ODYSSEY-X86J4105 Unboxing I received ODYSSEY-X86J4105864 with a built-in 64GB eMMC flash pre-loaded with Windows 10 Enterprise. Let’s have a quick look at the board with USB, Ethernet and video output ports previously described, as well as built-in dual-band Wi-Fi 5 & Bluetooth 5.0 module, and […]

BeagleBone Green Gateway SBC with Ethernet, WiFi, and Bluetooth Launched for $60

BeagleBone Green Gateway SBC was first unveiled last July as an update to BeagleBone Green Wireless board with Ethernet, and Octavo Systems OSD3358 SiP along with some smaller changes like support for 12V power supply and I2C RTC + battery. The board did however lose two USB 2.0 ports to make space for the Ethernet connector. The board was not quite available at the time, but the good news is that you can now buy BeagleBone Green Gateway for $59.99 on Seeed Studio. Specifications have remained the same as the ones provided for the initial announcement:  SiP – Octavo Systems OSD3358 with Texas Instruments AM3358 Arm Cortex-A8 processor @ 1.0 GHz, 2×32-bit 200-MHz programmable real-time units (PRUs), 3D graphics accelerator, 512MB DDR3 SDRAM, 4KB EEPROM, and integrated power management Storage – 4GB 8-bit eMMC on-board flash storage (Kington) + microSD socket Connectivity 10/100Mbps Ethernet (RJ45) WiFi 802.11 b/g/n 2.4GHz + […]

Nubix Edge-native Tiny Containers for IoT Apps Released For Raspberry Pi and BeagleBone SBCs

Nubix has just launched the developer edition of its edge-native tiny containers for IoT application development and analytics that target microcontrollers and single-board computers such as Raspberry Pi 3/4 and BeagleBone Black. Typical cloud solutions such as Docker are often too large with tiny IoT devices, and to solve these issues, Nubix tiny containers are sized in kilobytes, instead of megabytes, or about 100 times smaller than a Docker container, in order to be small enough to run at the edge. provides access to a library of sensors, analytics and tiny services that leverage open source languages and pre-packaged functions to easily create IoT applications in a few minutes. Analytics is commonly done in the cloud, which may cause issues in environments with limited or intermittent connectivity, so to solve this issue, Nubix provides analytics functionality directly on the IoT device, eliminating the latency, bandwidth, connectivity and cost constraints […]

$118 BeagleBone-AI SBC is Made for AI Edge Applications

The Foundation introduced BeagleBone-AI SBC at Embedded World 2019 last February. The board is specifically designed for artificial intelligence workloads at the edge thanks to Texas Instruments AM5729 dual-core Cortex-A15 processor that embeds a dual-core C66x DSP, and 4 EVE (Embedded Vision Engine) cores. The BeagleBone Black compatible board was not available at the time,  but the Foundation has now formally launched the board, and you can buy BeagleBone-AI for $118 and up with heatsink and antenna on sites such as Mouser, OKdo, or Newark. BeagleBone-AI full specifications have now been published: SoC – TI Sitara AM5729 with Dual-core Cortex-A15 processor @ 1.5 GHz 2x dual-core PRUs 2x Cortex-M4 real-time cores dual core C66x VLIW DSP 4x EVEs 2.5MB of on-chip L3 RAM VA-HD subsystem with support for 4K at 15fps H.264 encode/decode and other codecs at 1080p60 Vivante GC320 2D graphics accelerator Dual-Core PowerVR SGX544 3D GPU System […]