Home Community Blog Buy Now

Misty Community Forum

2021.05.12 Release Notes

Greetings, Misty developers!

A small but mighty release with a few new features and bug fixes. The major change in this release is small under the hood but has a big impact. We are changing the default Misty-created wake word (“Hey Misty”) to a new Azure-generated wake word (still “Hey Misty”) that is showing much better performance. We are also updating the microphone input volume to its maximum, which will improve audio input. The result of both of these changes is improvements to speech skills when activating Misty with “Hey Misty” and then using speech input. In the process of this we’ve discovered a few bugs that we’ve fixed, see details below.

Thanks, as always, for being an early developer for the Misty II platform. We can’t wait to see what you build!

Installing the Update

Misty receives software upgrades as over-the-air (OTA) system updates. This update will be available within the next 24-48 hours (the precise timing varies by region).

Misty automatically checks for new updates each time she boots up. As long as her battery has enough charge, she automatically installs any updates that are available. If your robot doesn’t start to install this update the next time she boots up:

  • Check that Misty is connected to power or sitting on her wireless charging station.
  • Try connecting Misty to the Command Center to make sure she’s still on your Wi-Fi network.

If Misty is charging and connected to the internet, you can check whether an update is available in your region by connecting Misty to the Command Center and looking at the System Updates section.

Note: Misty reboots once during a system update. During an update, Misty ignores all commands except Halt and Stop. If Misty starts installing an update while charging, do not remove the power source until the update is finished and Misty’s eyes are fully open.

If you have issues with a system update or need technical assistance for other reasons, for the quickest response you can:

  • Post a message to the Support category here in the Community forums.
  • Contact with the Misty support team through the chat embedded in this site, or by emailing support@mistyrobotics.com.

Release Contents

  • Misty II - Updates
    • Window IoT Core OS version: 10.0.17134 or higher - No updates
    • Android OS: (8.1) - No updates
    • Robot Version:
    • MC Version:
    • RT Version:
    • Sensory Services App Version: 1.24.9
  • Web-based Tools - No updates.
  • Misty JavaScript Extension for VSC - No updates.
  • Misty App - No updates.
  • Documentation - No updates.

New Features

  • Dramatic improvement to the “Hey Misty” wake word by updating the default keyphrase to Azure. The wake word will still be “Hey Misty”, it will just work much better than the previous phrase. You should have many fewer failures (e.g. it will trigger without you having to repeat) and fewer false positives (won’t activate when it shouldn’t) than the previous version. Here’s what we’re changing:
    • Changes the default keyphrase recognition engine to Microsoft.
    • Adding new Azure-generated wake word file /sdcard/audio/hey_misty.table and updating the config to use this new wake word
    • Previous wake word at /sdcard/audio/keyphrase.table will remain on the robot and you can update the config to switch back if you have generated your own or a different wake word
  • Improved Misty’s ability to hear by changing the default microphone input volume to 100 (from a previous 84). This should result in better audio recording quality of all inputs into the robot and give you better results from third-party speech services.

Bug Fixes & Improvements

  • Found an issue when copying files to change microphone volume where it could result in corrupted mixer files. This has been fixed.
  • When calling the SetMicrophoneMixerDECVolume and SetMixerFile commands, previously it would sometimes say it failed when it was just processing. This should be fixed now, if it says it failed it probably did.

Known Issues

The following is a list of new known issues with this release. For a comprehensive list of the issues we’re tracking, see the Known Issues section of the Community forums.

  • No known issues.

can you clarify the meaning of “Azure-generated”?

mostly I am concerned about whether an Internet connection will now be required.

An internet connection is not required for this speech recognition.

The Azure-generated is clarifying that it is using Azure Custom Keyword functionality mentioned in these release notes. Which uses the custom keyword model generated from the Azure Speech Studio. The model is ran locally on the robot but utilizes the file referenced above to function properly.