Picovoice on-device speech-to-text engines slash the requirements and cost of transcription

Speech-to-text benchmarks accuracy

Picovoice Leopard and Cheetah offline, on-device speech-to-text engines are said to achieve cloud-level accuracy, rely on tiny Speech-to-Text models, and slash the cost of automatic transcription by up to 10 times. Leopard is an on-device speech-to-text engine, while Cheetah is an on-device streaming speech-to-text engine, and both are cross-platform with support for Linux x86_64, macOS (x86_64, arm64), Windows x86_64, Android, iOS, Raspberry Pi 3/4, and NVIDIA Jetson Nano. Looking at the cost is always tricky since companies have different pricing structures, and the table above basically shows the best scenario, where Picovoice is 6 to 20 times more cost-effective than solutions from Microsoft Azure or Google STT. Picovoice Leopard/Cheetah is free for the first 100 hours, and customers can pay a monthly $999 fee for up to 10,000 hours hence the $0.1 per hour cost with PicoVoice. If you were to use only 1000 hours out of your plan that […]

Khadas Tea – A MagSafe Hi-Fi headphone amplifier to play lossless audio on smartphones (Crowdfunding)

From this side of the Internet, Khadas is better known for their single board computer, but the company has also made Hi-Fi audio products starting with the Khadas Tone in 2018 as an add-on board for Khadas VIM/VIM2 SBC, followed by Khadas Tone 2 Pro mini desktop Hi-Fi system in 2020. The latest audio product from Khadas is a smartphone accessory with Khadas Tea being a thin MagSafe-compatible magnetic Hi-Fi headphone amplifier based on aptX HD and LDAC capable Qualcomm QCC5125 Bluetooth SoC and ESS ES9281AC Pro DAC that sticks to the back of your phone. Khadas Tea specifications: Bluetooth Audio SoC – Qualcomm QCC5125 Bluetooth 5.0 audio chipset USB DAC – ESS ES9281AC Pro Amplifier – RT6863D (Buffer Stage) Audio I/O 3.5mm headphone jack Built-in stereo microphone for making and receiving calls over Bluetooth Sampling Rate USB: up to 32bit 384KHz @ PCM, or DSD 256 (Native) Bluetooth: up […]

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, libpv_cobra.so 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 […]

Review of FamiSafe Phone Tracking & Parental Control App (Sponsored)

CNXSoft here. I’ve been tasked with reviewing Famisafe parental control app for Android and iOS acting both as a parental control app and phone tracker app and designed for parents who want to track their kids’ location and better control when to use the phone and what content they may access. The first thing to get started is to download the free trial on either Android or iOS. I actually downloaded both versions for FamiSafe for this review, since I used Huawei Y9 Prime 2019 (Android 10) as the “parent” smartphone, and an iPhone 6 as the “kid” phone. Famisafe Initial Configuration We’ll have to start with the “parent” phone. After a welcome screen explaining some of the main features including offensive content detection, device & app usage rules, web filter, etc.. you’ll be asked to select whether it’s the parent or kid device. Once we select “Parent” we’ll be […]

ESP RainMaker Eases Cloud Integration & Mobile App Development for ESP32-S2 SoC

Espressif Systems is well-known for its low-cost, well-supported WiFI and Bluetooth SoC for IoT products and projects. But in recent years, the company has also come up with application-specific development boards and corresponding software frameworks to help customer develop their own. Those boards include ESP32-LyraTD-MSC for smart audio applications, or for ESP32-S2-Kaluga-1 multimedia applications using display and camera. The company is now offering another solution to help makers integrate ESP32-S2 secure WiSoC with the cloud and create a mobile app. Meet ESP RainMaker. Specifically, ESP RainMaker provides four main components:: Device Agent SDK to perform network provisioning, OTA updates and facilitate communication with the cloud. Based on the ESP-IDF SDK. Amazon’s AWS powered Transparent Cloud Middleware makes the device’s attributes accessible to the user’s phone applications or other third-party services via RESTful APIs. iOS/Android phone apps to configure and manage the connected device. The apps are “self-adapting”, meaning they can […]

$7 Sonoff D1 Smart Dimmer Switch Supports Mobile App, RF433 Remote, and Voice Assistants

ITEAD Studio Sonoff is a family of WiFi or/and 433 MHz RF connected smart home switches, sockets, light bulbs or other products for home automation. They are usually based on ESP8266 WiSoC and while the pre-loaded firmware works with eWelink Android/iOS app and popular voice assistant, it’s also possible to load open-source firmware such as Sonoff-Tasmota or ESPurna to add MQTT and other protocols in order to integrate those with home automation solution such as Domoticz, or something control those from your web browser. The company has now launched another Sonoff device, namely Sonoff D1 smart dimmer switch which – as its name implies – will allow you to dim incandescent and dimmable LED lights. Sonoff D1 smart dimmer switch specifications: Connectivity – RF433 and 802.11b/g/n WiFi 4 Max Current – 1A Max Power – 400W for Incandescent lamp, and 150W for LED light Power Supply – 110V-230V AC input […]

Tiny USB WiFi Camera Supports Motion and AI Human Detection

When I first saw U21 HD camera it reminded me of SOOCOO G1 is action camera with a flexible stick, since the camera also comes with a flexible hose which allows you to orient it as you please. But it’s a different bear, as U21 is a surveillance camera powered over USB and featuring WiFi connectivity. I can’t see any motion detection, so it may have some dose of “AI” since it claims to support motion and human detection so you only get relevant alerts. It is currently sold (pre-orders) on Banggood for $33.65 including shipping with order starting to be processed on October 30th. U21 USB WIFI camera key features and specifications: MCU / WiSoC – No information (yet) Storage – MicroSD card slot up to 128GB for up to one month of recording (8GB = 2 days); Cloud storage via third party (paid) Camera – 14mm lens, HD […]

PUCK 2 Bluetooth to IR Bridge Allows you to Control Appliances from your Android or iOS Phone

We’ve already seen there are several solutions to control IR appliances such as air conditioners or (dumb) televisions via your smartphone thanks to solutions such as ZaZa Remote  that adds an IR transmitter to your 3.5mm audio jack or more recently via your USB-C port. If you don’t quite like having extra hardware connected to your smartphone WiFi to Infrared bridges such as the compact and omnidirectional Broadlink RM Mini 3 are cost-effective solutions, although you’d need one in every room where you wish to control appliances. I’ve recently noticed an even smaller “smartphone to IR” solution with PUCK v2 Bluetooth to IR bridge. The full technical details about PUCK 2 have not been made available, but we do know it’s a Bluetooth 4.2 to infrared remote bridge that transforms any iOS or Android device into a remote. The infrared LED has a range of about 4.5 meters, while Bluetooth […]