EasyVR 3 Plus is a multi-purpose speech recognition module designed to easily add versatile, robust and cost effective speech recognition capabilities to almost any application.

The EasyVR 3 Plus module can be used with any host with a UART interface powered at 3.3V – 5V, such as PIC and Arduino boards. Some application examples include home automation, such as voice-controlled light switches, locks, curtains or kitchen appliances, or adding “hearing” to the most popular robots on the market.

EasyVR 3 Plus allows up to 256 user-defined Speaker Dependent (SD) or Speaker Verification (SV) commands, that can be trained in ANY language, divided into maximum 16 groups (up to 32 SD or 5 SV commands each).

A selection of 26 built-in Speaker Independent (SI) commands for ready-to-run basic controls, in the following languages:

• • English (US)
  • Italian
  • German
  • French
  • Spanish
  • Japanese

See other SI commands downloadable for free.
With the optional Quick T2SI Lite license, up to 28 custom Speaker Independent (SI) command vocabularies, with up to 12 commands each, for a total of 336 possible commands.

Supported languages:

• • US English
  • French
  • German
  • Italian
  • Japanese
  • Mandarin
  • Spanish

Please note: The Quick T2SI Lite license registration code is sold separately and is available for sale from your distributor or directly from us: please send an email to our sales if you are interested.

It can be easily plugged into a solder-less breadboard or standard prototyping board, and it is compatible with the mikroBUS™ specifications (see www.mikroe.com/mikrobus).

Separate male headers are provided inside the package, along with a microphone cable assembly and speaker wires (loudspeaker not included).

• SonicNet™ technology for wireless communications between modules or any other sound source (Audio CD, DVD, MP3 Player).
• Up to around 21 minutes of pre-recorded sounds or speech .
• Up to about 137 seconds of live message recording and playback .
• Real-time Lip-sync capability .
• DTMF tone generation.
• Differential audio output that directly supports 8Ω speakers.
• Easy-to-use Graphical User Interface to program Voice Commands and audio.
• Standard UART interface (powered at 3.3V – 5V).
• Simple and robust documented serial protocol to access and program through the host board.
• 6 General purpose I/O lines that can be controlled via UART commands.

NOTE:
The headers are not assembled and need to be soldered if needed.
The microphone and the speaker wire with connector are delivered along with the board, the speaker is not included.

SD/SV commands are entirely user-defined and they are intended to work only with the voice that trained them. SD only tries to match the trained words, while SV also tries to match the characteristics of the voice and to prevent use by unknown people (voice password).

SI commands are meant to work with any people in the same language group and do not require training. A few pre-defined commands can be directly used, while additional commands can be created with a QuickT2SI™ Lite license (sold separately).