INTRODUCTION
What is voice recognition?
Voice recognition is a computer technology that recognizes and converts speech signals into editable text or operational commands through analysis. It allows people to interact with computers by speaking without using a mouse, keyboard, or other input devices. Voice recognition technology has been widely used in applications such as voice assistants, smart homes, voice search, and voice recognition notebooks.
Product Introduction
This Gravity: Offline Voice Recognition Sensor is built around an offline voice recognition chip, which can be directly used without an internet connection. It comes with 121 built-in fixed command words and supports the addition of 17 custom command words. Any sound could be trained as a command, such as whistling, snapping, or even cat meows, which brings great flexibility to interactive audio projects.
The module features a dual microphone design with better noise resistance and a longer recognition distance, making it relatively accurate and reliable even in noisy environments. It comes with a built-in speaker and an external speaker interface for real-time voice feedback of recognition results. The module uses both I2C and UART communication methods and supports various 3.3V or 5V controllers, including the Arduino UNO, Arduino Leonardo, Arduino MEGA, FireBeetle series, and more.
This voice recognition module provides a reliable and flexible voice interaction solution for makers and electronics enthusiasts, and it can be applied to any applications where voice control or interaction is desirable, such as all kinds of smart home appliances, toys, lamps, and robotics projects.
Difference between offline and online voice recognition
An important factor in voice recognition is the voice database, which is used as comparative data during the recognition process. Online voice databases are stored in the cloud and have a very large amount of data, while offline voice databases are local and have limited space.
The pros and cons of offline and online voice recognition:
| Pros | Cons | |
| Offline Speech Recognition | 1. Quickly respond to corresponding command words and instructions. 2. No need for a network. 3. If speech recognition fails, it will not affect the use of other product functions. 4. More secure privacy, users don’t have to worry about their conversation content being recorded and uploaded to the cloud. 5. Small module size, convenient for embedding in applications. 6. Cheaper price. | Command words are fixed, and there may be limitations on the number and length of words. |
| Online Speech Recognition | 1. Consumers are easy to use and not limited to command words. 2. Easy to develop, and there are many solutions in the market. | 1. Requires network connection to connect to the cloud. 2. Response speed depends on the network speed. 3. Higher cost. |
FEATURES
- Self-learning function: Control the module to learn command words by the voice, and any audio can be trained as a command
- Support I2C and UART, with a Gravity interface
- Compatible with 3.3V/5V
- Built-in with 121 commonly-used fixed command words
- The module has a built-in speaker and an interface for an external speaker, which can provide real-time voice feedback on recognition results
- Equipped with power indicator (red) and recognition status indicator (blue)
- Dual microphones provide better noise resistance and longer recognition distance
- Compatible with Arduino controllers: Arduino UNO, Arduino Leonardo, Arduino MEGA, FireBeetle series controllers, Raspberry Pi, ESP32
APPLICATIONS
- Voice recognition interaction
- Voice-controlled terminal
- Competition and project development
SPECIFICATION
- Operating Voltage: 3.3 – 5V
- Maximum Operating Current: ≤370 mA (5V)
- Communication: I2C/UART
- I2C Address: 0x64
- Fixed Command: 121
- Fixed Wake-up Command: 1
- Custom Command: 17
- Learning Activation Command: 1
- Onboard Microphone Sensitivity: -28db
- Module Size: 49×32 mm/1.93×1.26”
