Free tools Windows power users keep installed
One-click scans. No signup required.
You can build a small car that responds to spoken movement commands by combining an ESP32, a microphone or audio board, speech-recognition software, a motor driver, and a suitable chassis and power supply. The key is to keep speech recognition separate from motor actuation: the ESP32 interprets a command and sends control signals, while an H-bridge switches the current needed by the motors. Do not connect traction motors directly to ESP32 GPIO pins.
How an ESP32 voice-controlled car works
The system has four stages: audio input, command recognition, motion logic, and motor control. A microphone captures speech; software recognizes a phrase such as “forward” or “stop”; firmware maps that phrase to a motion state; and GPIO/PWM signals tell a motor driver how to run the wheels.
Espressif’s [FOFOCA reference design](https://developer.espressif.com/blog/2025/09/fofoca/) illustrates the separation: it uses an ESP32 for control, two DC motors and a dual H-bridge for movement, and a separate microphone array for audio input. Its parts are examples, not universal component recommendations.
Choose how the car will recognize speech
| Approach | How it works | Trade-offs |
|---|---|---|
| ESP-SR offline recognition | Run supported wake-word and command-recognition models on an ESP32 target. | Can work without sending speech to a cloud service, but the supported chip, model, language, and firmware configuration matter. Espressif’s basic ESP32 example uses English commands and the wake phrase “Hi ESP”; after a listening timeout, it may require another wake phrase. [Getting Started — ESP-SR for ESP32](https://docs.espressif.com/projects/esp-sr/en/latest/esp32/). [ESP-SR repository](https://github.com/espressif/esp-sr) |
| Phone, network, or computer recognition | An external device or service recognizes speech, then sends a short movement command to the ESP32. | May allow richer recognition, but depends on the selected service, connectivity, latency, and its privacy terms. The appropriate service depends on the project; there is no universally preferred option established here. |
| Small sound or analog classifier | Use signal processing or a classifier to distinguish a limited set of audio patterns. | Can suit a very small command set, but is not equivalent to general speech recognition and may be sensitive to speaker, microphone, gain, and background noise. |
| Prebuilt ESP32 robot car | Start with a commercial platform that advertises voice interaction. | Check the exact version, included audio hardware, voice behavior, programming access, and parts before comparing it with a DIY build. Hiwonder describes Tankbot as an ESP32 robot car with voice interaction. [Hiwonder Tankbot](https://www.hiwonder.com/products/tankbot) |
What parts you need
- ESP32 board: Choose a target supported by the speech-recognition approach and firmware you plan to use.
- Microphone and audio path: The microphone or audio board must be compatible with the selected ESP32 and recognition setup. Espressif recommends ESP32-Korvo for its ESP32 ESP-SR getting-started path; ESP32-LyraTD-MSC is a separate audio-focused board described with a three-microphone array and voice features. Neither is, by itself, a complete car chassis and controller package. [ESP32-LyraTD-MSC](https://docs.espressif.com/projects/esp-adf/en/latest/design-guide/dev-boards/user_guide_lyratd_msc.html)
- Chassis and motors: Use a chassis with two or more DC motors, wheels or treads, and mounting space for the electronics.
- Motor driver: Select an H-bridge rated for the motors’ supply voltage and stall current. The ESP32 supplies control signals; the driver handles motor current.
- Battery and regulation: Plan motor and ESP32 power around their electrical requirements. Do not choose a battery based only on a kit photograph or assume the motor supply is suitable for the ESP32.
- Optional obstacle sensing: A distance sensor or bumper switch can provide an additional stop input. Espressif’s FOFOCA design lists HC-SR04 ultrasonic sensors, but that does not make it a safety-certified design.
- Firmware environment: For Espressif’s local recognition route, plan to use ESP-IDF and ESP-SR. Espressif says ESP-SR is obtained with ESP-SKAINET and points to its speech-command example. [ESP-SR Getting Started](https://docs.espressif.com/projects/esp-sr/en/latest/esp32/)
Check recognition compatibility and storage first
ESP-SR offers WakeNet wake-word detection and MultiNet speech-command recognition, but features depend on the target chip and selected model. Consult Espressif’s current support information for the exact ESP32 family and ESP-SR release before committing to a language, model, or command count. [ESP-SR repository](https://github.com/espressif/esp-sr)
Recommended Free Tools
#1 Best Overall
- 2.4GHz Dual Mode WiFi + Bluetooth Development Board
- Support LWIP protocol, Freertos
- SupportThree Modes: AP, STA, and AP+STA
- Ultra-Low power consumption, Compatible with Arduino IDE
- ESP32 is a safe, reliable, and scalable to a variety of applications
Model files also need room in flash. Espressif’s model-selection documentation shows a 6000K partition allocation as an example and says to customize it for the selected models; it is not a universal requirement. Configure the selected models in menuconfig and verify that the chosen partition layout has enough space. [ESP-SR model selection](https://docs.espressif.com/projects/esp-sr/en/latest/esp32/model_choose.html)
The ESP-SR repository says MultiNet supports up to 300 Chinese or English speech commands. That is a stated capability, not a promise that every model and target combination can use all 300; the basic ESP32 getting-started example is English-only. Espressif’s example states: “The example only supports commands in English.” [Getting Started — ESP-SR for ESP32](https://docs.espressif.com/projects/esp-sr/en/latest/esp32/)
Rank #2
- Dual-Core Performance Up to 240 MHz: Run sensor processing, wireless communication, automation logic and connected-device tasks on a 32-bit dual-core ESP32 platform designed for responsive embedded and IoT projects
- Built-in Wi-Fi and Bluetooth 4.2: Connect to 2.4 GHz Wi-Fi networks or use Bluetooth Classic and BLE for wireless sensors, smart devices, remote controls, home automation and other connected projects
- Flexible Power-Saving Modes: ESP32 power-management features support dynamic clock scaling and low-power operating modes, helping developers reduce energy use in compatible sensing, monitoring and connected-device applications, suitable for battery-powered Internet of Things (IoT) devices.
- USB-C Programming with CP2102: Connect through USB-C for power, sketch uploads and serial monitoring, while GPIO, UART, SPI and I2C interfaces support sensors, displays, motor drivers and other modules (USB-C cable not included)
- Over-the-Air Update Support: Configure OTA functionality through a compatible ESP-32 software framework to update deployed firmware over Wi-Fi without reconnecting the board by USB for every revision
Implement a small, explicit motion vocabulary
Start with a short set of states—forward, reverse, left, right, and stop—rather than trying to interpret arbitrary conversation. Keep recognition output separate from motor control: the speech layer should produce a known command, and the motion layer should decide what signals are safe for the car.
- Initialize the audio input and load the recognition models.
- If using a wake word, wait for it before accepting a movement command.
- Map recognized phrases to the explicit motion states used by the car.
- Apply a speed limit and command timeout; return to stop if a command expires or communication fails.
- Translate the active state into direction and PWM signals for the H-bridge.
- Choose whether the driver should coast or brake when stopping, based on its capabilities and the vehicle design.
Timeouts and a fail-to-stop state are design recommendations, not measured outcomes for a particular build. Espressif’s getting-started example documents that command listening can time out after a wake word, so firmware should handle the end of a listening window deliberately.
Rank #3
- Powerful ESP-32 Board: Unlock the world of Internet of Things (IoT) and advanced electronics with the heart of this kit: the ESP-32 board. It features a powerful dual-core processor, integrated Wi-Fi and Bluetooth 4.2, making it perfect for building connected, smart devices that communicate with your phone or the cloud. It's fully compatible with the Arduino IDE for easy programming.
- Super Starter Kit: This kit contains over 35 different modules and electronic components, including sensors, displays, motors, and input devices. From LEDs and buttons to an OLED screen, servo motor, and keypad, you have everything needed to explore a vast range of projects in one box.
- Step by Step Online Tutorial: Jump right in with our detailed, beginner-friendly tutorial. Access 30+ projects with complete code, clear circuit diagrams, and step-by-step instructions. Learn the fundamentals of electronics, coding, and how to utilize the ESP-32's unique capabilities without any prior experience.
- Hands-on Learning for All Skill Levels: Perfect for students, makers, engineers, and hobbyists. Start with basic circuits and coding, then progress to intermediate and advanced IoT applications. Build practical projects like weather stations, smart home controllers, remote-controlled devices, and interactive gadgets. The skills you learn are the foundation for real-world innovation.
- Quality & Great Support: Elegoo is committed to quality. We provide a clear, detailed tutorial guide, refined code, and a well-organized component kit. All modules are carefully selected for reliability and ease of use. Our dedicated technical support team and active online community are ready to help you succeed in your learning journey.
Do not assume a robot-car kit includes voice control
A kit can supply useful movement hardware without including a microphone or voice firmware. The LAFVIN manual for an ESP32 robot smart-car kit lists an L298N driver, TT motors, chassis hardware, and a battery case; those contents do not establish that the kit includes audio input or voice-control software. Check the exact listing and add compatible audio hardware and software if needed. [LAFVIN ESP32 robot smart-car manual](https://www.lafvintech.com/wp-content/uploads/2020/06/ESP32-Robot-Car-Kit-Manual.pdf)
Before buying parts, compare the ESP32 target and firmware support, language and command vocabulary, microphone interface, flash needs, driver-to-motor electrical match, battery arrangement, obstacle-sensing needs, and access to editable code. Product bundles and current prices can change, so verify the exact version you intend to use.
Rank #4
- 2.4GHz Dual Mode WiFi + Bluetooth Development Board
- Support LWIP protocol, Freertos;ESP32 is a safe, reliable, and scalable to a variety of applications
- SupportThree Modes: AP, STA, and AP+STA
- Ultra-Low power consumption, Compatible with Arduino IDE
- 1PCS 30Pin ESP32 Development Board 2.4GHz WiFi Dual Cores Microcontroller Integrated with Antenna RF Low Noise Amplifiers Filters
What published example costs do—and do not—tell you
Espressif’s 2026 FOFOCA parts list estimates USD 20 for two geared motors with treads, USD 3 for an HW130 dual H-bridge, USD 30 for a ReSpeaker USB Mic Array, and USD 5 for an ESP32 DevKit v1. These are estimates in that project’s bill of materials, not a quote for a small voice-controlled car or guaranteed current retail prices. The same article estimates about USD 650 for its much larger overall setup and explicitly excludes repurposed Dell server and Insta360 equipment, so that total is not a sensible small-car budget target. [FOFOCA parts list](https://developer.espressif.com/blog/2025/09/fofoca/)
Quick Recap
Best Value
- 2.4GHz Dual Mode WiFi + Bluetooth Development Board
- Ultra-Low power consumption, works perfectly with the Arduino IDE
- Support LWIP protocol, Freertos
- SupportThree Modes: AP, STA, and AP+STA
- ESP32 is a safe, reliable, and scalable to a variety of applications
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
