ver.3.9.4 * Bug fixes - The LLM settings are not being properly applied to the character, causing it to stop responding. ver.3.9.0 * Support Grok API * Changed default versions for each LLM model * Added motion effects during music playback - Added penlight (SAKAYA3D "Light-Up Penlight") - Changed Bloom setting to default 1.0 * Added 50 new motion animations (From Kagura Moi "Moiland Animation 100") * Bug fixes - Minor bug fixes

ver.3.9.2 * Update Azure TTS SDK ver.3.9.1 * Bug fixes - Sometimes the chair does not disappear after the character stands up from it. ver.3.9.0 * Support Grok API * Changed default versions for each LLM model * Added motion effects during music playback - Added penlight (SAKAYA3D "Light-Up Penlight") - Changed Bloom setting to default 1.0 * Added 50 new motion animations (From Kagura Moi "Moiland Animation 100") * Bug fixes - Minor bug fixes

ver.3.9.1 * Bug fixes - Sometimes the chair does not disappear after the character stands up from it. ver.3.9.0 * Support Grok API * Changed default versions for each LLM model * Added motion effects during music playback - Added penlight (SAKAYA3D "Light-Up Penlight") - Changed Bloom setting to default 1.0 * Added 50 new motion animations (From Kagura Moi "Moiland Animation 100") * Bug fixes - Minor bug fixes

ver.3.9.0 * Support Grok API * Changed default versions for each LLM model * Added motion effects during music playback - Added penlight (SAKAYA3D "Light-Up Penlight") - Changed Bloom setting to default 1.0 * Added 50 new motion animations (From Kagura Moi "Moiland Animation 100") * Bug fixes - Minor bug fixes

ver.3.8.1 * Added checkboxes to enable/disable face recognition * Bug fixes - Voice and command recognition cannot be executed while face detection is in progress. - Minor bug fixes

ver.3.8.0 * Added user registration functionality (name, face recognition) * Unified character voices to synthetic speech when using the "Scenario/LLM" dialog method * Renamed the "Scenario/LLM" dialog method to "LLM function calling" * Bug fixes - Minor bug fixes - Voice Settings > VOICEOVOX: test audio did not play when using an external web API - AI (LLM) Llama does not work properly

* ROS2 (Robot Operating System 2) /std_msgs/msg/String Send and receive support (TCP-ROS-Connection / TCP-ROS-Endpoint support) * Function improvements - Improvements in response editing screen(changed so that 20 responses can be created) * Bug fixes - Minor bug fixes - Fixed a bug where the settings could not be saved after being cleared in response editing

* ROS2 (Robot Operating System 2) /std_msgs/msg/String Send and receive support (TCP-ROS-Connection / TCP-ROS-Endpoint support) * Function improvements - Improvements in response editing screen(changed so that 20 responses can be created) * Bug fixes - Minor bug fixes

* Support Claude, Llama API * Function improvements - Speech recognition start and response time - Lip-sync support when editing responses using external speech data loading - UI icon changes (scenario indicator, speech recognition microphone) - Added some effects * Bug fixes - Some character models are not displayed in ViewScene - In some cases, learned responses may not be executed correctly

* Support Geminit API * Function changed - Changed ChatGPT settings to AI prompt (LLM) settings menu. - The setting for enabling/disabling "Function calling" has been removed. If the conversation type is "LLM", function calling is disabled. If the conversation type is "Scenario/LLM", function calling is enabled. * Bug fixes - The value of the Azure TTS ApiKey setting is incorrect in the Voice settings. - In some cases, lip-sync does not work properly with some character models. - When the cache of the VRoidHub model data is corrupted, the model is not displayed.

Added functions - Make a phone call - Screen keyboard button Fixed minor bugs

* Bug fix * When the conversation type is "dialogue scenario only," there are cases in which the character does not learn correctly. See the release notes on https://acuah.info for details.

* Added Learning function using return value of ChatGPT function calling arguments. * Added Simple delete function for learned data. See the release notes on https://acuah.info for details.

* Added Photo and Photo album function. * Added QR code reader function. (Added the screen for the character assistant to see the real world.) * Fixed a bug that may not handle ChatGPT responses properly. * Fixed a bug that the character assistant doesn't wakeup (appear) from sleeping before for waking the user up. See the release notes on https://acuah.info for details.

* Fixed a bug that conversation type settings were not saved properly. * Added setting to use ChatGPT Function calling. See the release notes on https://acuah.info for details.

* Added ChatGPT multiple prompts editing function * Added voice data set setting function. * Support VRMA (VRMAnimation) motion data loading And other functional improvements and bug fixes. (See the release notes on https://acuah.info for details.)

* Fixed a bug that caused collapsed images in notepad.