
LogicAnalyzer
gusmanb/logicanalyzer
24 channel, 100Msps logic analyzer hardware and software

HHD3.0
OutHouse is an open-source printed circuit board by BharathKrishna0078, from the BharathKrishna0078/Vaacha repository on GitHub. It is a 2-layer board of 100.8 × 91 mm with 10 parts on 9 nets, routed with 78 tracks and 1 via.
Vaacha (वाचा) = "speech/voice" in Sanskrit — giving voice to the voiceless
VAACHA is a handheld hardware device that enables two-way communication between deaf/hard-of-hearing individuals and hearing people — across any Indian language — without an interpreter.
| Direction | Flow |
|---|---|
| Deaf → Hearing | ISL gesture → TinyML on ESP32-S3 → Sarvam TTS → spoken audio |
| Hearing → Deaf | spoken audio → Sarvam STT → Sarvam Translate → OLED text display |
One device. Two-way communication. 11 languages. No cloud required for gesture recognition.
See
VAACHA-PRD.mdfor the full Product Requirements Document.
18 million deaf and hard-of-hearing Indians cannot communicate independently at doctor visits, bank counters, railway ticket windows, or any daily transaction — because there are only ~300 certified ISL interpreters in all of India.
Existing tools fail because India has 22 official languages. Even if a device "understands" ISL and outputs text, it can't bridge a deaf Tamil woman speaking to a Hindi-speaking doctor.
The device runs on two ESP32 modules mounted on a custom-designed carrier PCB:
| Board | Role |
|---|---|
| ESP32-CAM (OV2640) | Captures gesture frames → sends via UART to Glyph S3 |
| Glyph S3 (ESP32-S3) | Main brain — TinyML inference, audio I/O, OLED, buttons, WiFi to laptop |
The ESP32-S3 connects to a laptop over local WiFi (no internet) via WebSocket. The laptop runs the Sarvam AI pipeline.
[VAACHA Device] [Laptop Hub]
ESP32-CAM Python App
└─UART→ Glyph S3 (TinyML) ├── Sarvam STT
└──── WiFi/WebSocket ──────► ├── Sarvam TTS
├── Sarvam Translate
└── Flask DashboardThe PCB (70mm × 50mm, 2-layer, KiCad 8) integrates:
Without the PCB: two dev boards on a breadboard.
With the PCB: a single integrated product you can hold in your hand.
| Parameter | Value |
|---|---|
| Framework | TensorFlow Lite Micro (via Edge Impulse) |
| Model | MobileNetV2 INT8 quantized |
| Input | 96×96 grayscale image |
| Output | 15 ISL gesture classes + confidence |
| Model size | ~200–300 KB |
| Inference time | 200–400 ms |
| Confidence threshold | 0.75 |
| # | Gesture | Meaning |
|---|---|---|
| 1 | Open palm wave | Hello |
| 2 | Thumbs up | Yes |
| 3 | Thumbs down | No |
| 4 | Both palms up | Help |
| 5 | Point to self | Me/I |
| 6 | Flat hand to mouth | Food/Eat |
| 7 | Cupped hand to mouth | Water/Drink |
| 8 | Fist to chest | Pain/Hurt |
| 9 | Cross arms | Stop |
| 10 | Palm forward push | Go/Leave |
| 11 | Point forward | You/There |
| 12 | Finger circle | Money/Pay |
| 13 | Roof shape | Home/House |
| 14 | Hand to ear | Listen/Hear |
| 15 | Open palm forward | Thank you |
vaacha-hub/)vaacha-hub/
├── main.py # Entry point — WebSocket server + dashboard
├── sarvam_pipeline.py # Sarvam STT, TTS, Translate, Language Detection
├── ws_server.py # WebSocket server (receives from ESP32 via WiFi)
├── audio_utils.py # ADPCM decode/encode, WAV conversion
├── dashboard/ # Flask live demo visualization
├── config.py # Language codes, API keys, WiFi settings
└── requirements.txt # sarvamai, websockets, flask| Sarvam API | Used For |
|---|---|
Text-to-Speech (/text-to-speech) | Gesture label → spoken audio in target language |
Speech-to-Text (/speech-to-text) | Transcribe hearing person's speech |
Translation (/translate) | Cross-language text conversion |
Language Detection (/detect-language) | Auto-detect what language was spoken |
Transliteration (/transliterate) | Display text in user-preferred script |
Supported output languages: Hindi, Tamil, Telugu, Kannada, Malayalam, Bengali, Marathi, Gujarati, Punjabi, Odia, English
| Mode | LED Color | What Happens |
|---|---|---|
| SIGN | 🟢 Green | Camera active → gesture classified → Sarvam TTS → speaker |
| LISTEN | 🔵 Blue | Mic active → Sarvam STT → translated text on OLED |
| IDLE | ⚪ White pulse | Low power, waiting for button press |
Toggle modes with a single button press. Language cycles with the other two buttons. Preference is saved to flash.
| Component | Purpose | ₹ |
|---|---|---|
| Glyph S3 (ESP32-S3) | Main MCU + TinyML + WiFi | 2,399 |
| OV2640 Camera (ESP32-CAM) | Gesture capture | (from organizers) |
| 1.3" I2C OLED (SH1106) | Text display | 499 |
| Condenser Mic | Audio input for STT | 20 |
| Speaker 0.5W 8Ω | Audio output for TTS | 150 |
| LiPo Battery | Portable power | 300 |
| Tactile buttons × 3 | Mode + language select | 30 |
| RGB LEDs × 2 | Status indicator | 20 |
| BC547, resistors, caps | Amp stage + filters + bias | 105 |
| Headers, wires, perfboard | Assembly | 110 |
| TOTAL | ₹3,633 |
₹367 buffer remaining from ₹4,000 hackathon budget.
Hardware Hackathon/
├── README.md ← You are here
├── VAACHA-PRD.md ← Full Product Requirements Document
└── PCB/ ← KiCad schematic + layout filesLOCALAI + HARDWARE — Edge AI running on the MCU (TinyML gesture classification on ESP32-S3), local AI on the laptop (Sarvam Edge models, offline), no cloud required for core functionality.
| Phase | Timeline | Milestone |
|---|---|---|
| v1.0 | Hackathon (3 days) | 15 gestures, laptop hub via WiFi, Sarvam Cloud API |
| v1.5 | +2 months | 50 gestures, fully offline with Sarvam Edge on laptop |
| v2.0 | +6 months | Android companion app with Sarvam Edge + BLE — no laptop needed |
| v2.5 | +9 months | 200 gestures, iOS app, dynamic gesture sequences |
| v3.0 | +12 months | AICTE/NCERT partnership for deaf schools, multilingual ISL dictionary |
| Role | Responsibility |
|---|---|
| Hardware Lead | KiCad PCB design, soldering, analog circuits |
| Firmware Dev | ESP-IDF / Arduino, FreeRTOS tasks, camera + audio I/O |
| ML Engineer | Edge Impulse training, TFLite model deployment |
| Software Dev | Sarvam pipeline, WebSocket server, Flask dashboard |
| Qty | Value | Footprint | References |
|---|---|---|---|
| 1 | U1 | glyph-s3 | U1 |
| 1 | U10 | R_Axial_DIN0207_L6.3mm_D2.5mm_P10.16mm_Horizontal | U10 |
| 1 | U2 | OLED_128X64_1.3 | U2 |
| 1 | U3 | ESP 32 CAM | U3 |
| 1 | U4 | SW_PUSH_6mm | U4 |
| 1 | U5 | SW_PUSH_6mm | U5 |
| 1 | U6 | gmod_lithium_charging_module | U6 |
| 1 | U7 | gmod-dc-dc | U7 |
| 1 | U8 | JST_EH_S2B-EH_1x02_P2.50mm_Horizontal | U8 |
| 1 | U9 | R_Axial_DIN0207_L6.3mm_D2.5mm_P10.16mm_Horizontal | U9 |

gusmanb/logicanalyzer
24 channel, 100Msps logic analyzer hardware and software

byrantech/laptop
anyon_e, a highly integrated, high end, open source laptop. Attempt the impossible.

joeycastillo/Sensor-Watch
A board replacement for the classic Casio F-91W wristwatch


OLIMEX/OLINUXINO
OLINUXINO is Open Source / Open Hardware, low cost from EUR 24 Linux Industrial grade Single Board Computer capable to operate -25+85C

rusefi/rusefi
rusefi - GPL internal combustion engine control unit

VoronDesign/Voron-Hardware
Cool Hardware designed by the Voron Design group

hoglet67/RGBtoHDMI
Bare-metal Raspberry Pi project that provides pixel-perfect sampling of Retro Computer RGB/YUV video and conversion to HDMI
It measures 100.8 × 91 mm and has 2 copper layers, 1.6 mm thick.
10 parts. The full list of its parts is on this page, with links to each part's symbol and footprint where PCBKit's library has them.
From the BharathKrishna0078/Vaacha repository on GitHub, at the commit this page was made from: the board is hardware/pcb/OutHouse.kicad_pcb. PCBKit opens the board in the browser, with nothing to install.
Its repository states no licence, so its author keeps all rights: ask BharathKrishna0078 before reusing the design.