esphome-box3-builder

Generates ESPHome configurations for ESP32-S3-BOX-3 display, touch, audio, and voice assistant hardware.

Updated Jun 11, 2026
One-click install
npx skills add https://github.com/brillianodhiya/VisionScript --skill esphome-box3-builder-brillianodhiya
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: esphome-box3-builder
Source: https://github.com/brillianodhiya/VisionScript/tree/main/.agents/skills/esphome-box3-builder
Command: npx skills add https://github.com/brillianodhiya/VisionScript --skill esphome-box3-builder-brillianodhiya

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires esphome, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve? Configuring the ESP32-S3-BOX-3 involves coordinating PSRAM, I2S audio codecs (ES7210/ES8311), an ILI9xxx display, and a GT911 touchscreen, where small mistakes cause boot failures, audio popping, or unresponsive touch. This Skill provides tested templates and hardware references so you avoid those pitfalls. ## Core Features & Use Cases - Ready-to-flash templates: Base hardware init, voice assistant with micro_wake_word, multi-page touchscreen UI, and media player configurations. - Display lambda cookbook: Text, shapes, Material Design icons, and multi-page navigation patterns for the 320x240 ILI9342C screen. - Hardware troubleshooting: Documented fixes for I2S DMA buffer errors, shared GPIO48 reset conflicts, PSRAM detection, and touch strapping pin warnings. - Use Case: Ask to build a BOX-3 voice assistant, and the Skill produces a complete YAML with wake word detection, Home Assistant Assist pipeline, audio ducking, and status LED feedback, then flashes it via the included script. ## Quick Start Ask the assistant to create an ESP32-S3-BOX-3 voice assistant configuration using the box3-voice template and flash it with the flash-box3 script.

Frequently Asked Questions about esphome-box3-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure ESP32-S3-BOX-3 with ESPHome?▼

Start from the box3-base template which includes ESP-IDF framework, octal PSRAM at 80MHz, the shared I2S bus, ILI9xxx display, and GT911 touch. Customize the device name and WiFi credentials, then validate and flash with the flash-box3 script.

How to set up a voice assistant on ESP32-S3-BOX-3?▼

Use the box3-voice template which configures micro_wake_word with okay_nabu, the voice_assistant pipeline with noise suppression and auto gain, plus audio ducking through the Nabu media player. It requires the ES7210 microphone at 16kHz and ES8311 speaker at 48kHz.

Why is PSRAM not detected on ESP32-S3-BOX-3?▼

ESPHome 2025.2 and later requires explicit PSRAM configuration. Add psram with mode octal and speed 80MHz to your YAML, since the BOX-3 has 16MB Octal PSRAM that is no longer auto-detected.

Why is the GT911 touchscreen not responding on BOX-3?▼

The touch reset pin GPIO48 is shared with the display and must be set to inverted true on both components. Also add ignore_strapping_warning true to the GPIO3 interrupt pin, and verify the I2C address is 0x5D or 0x14.

How do I fix audio popping on ESP32-S3-BOX-3 speaker?▼

Set buffer_duration to 100ms in the i2s_audio speaker configuration and confirm use_mclk is true for the ES8311 DAC. Verify sample rates are 16kHz for the microphone and 48kHz for the speaker.

Should I use ESP-IDF or Arduino framework for BOX-3?▼

ESP-IDF is recommended for the BOX-3 because it provides better audio and display support. Add execute_from_psram true under framework advanced options to prevent the UI from freezing during OTA updates.