Release notes
ACUAH (ver.3.0.0-)
ver.3.9.3
[10-7-2025]
- (Android) Security update
ver.3.9.2
[9-15-2025]
- (Android) Support 16KB page sizes
ver.3.9.1
[8-22-2025]
- Bug fixes
- Sometimes the chair does not disappear after the character stands up from it.
ver.3.9.0
[8-18-2025] (iOS) / [8-17-2025] (Android)
- Support Android 15
- 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 animations (From Kagura Moi "Moiland Animation 100")
- Bug fixes
- Minor bug fixes
ver.3.8.1
[6-21-2025]
- Added checkboxes to enable/disable face recognition
- Bug fixes
- (Android) When loading LocalVRM, data with the same file name is not updated
- Voice and command recognition cannot be executed while face detection is in progress
- Minor bug fixes
ver.3.8.0
[5-12-2025]
- 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
- Voice Settings > VOICEOVOX: test audio did not play when using an external web API
- AI (LLM) Llama does not work properly
- Minor bug fixes
ver.3.7.0
[2-28-2025]
- ROS2 (Robot Operating System 2) /std_msgs/msg/String send and receive support
- Function improvements
- Improvements in response editing screen(Configuration menu 3: changed so that 20 responses can be created)
- Bug fixes
- Minor bug fixes
ver.3.6.0
[1-18-2025]
- 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 when playing music
- Bug fixes
- Some character models are not displayed in ViewScene
- In some cases, learned responses may not be executed correctly
ver.3.5.0
[9-28-2024]
- Support Gemini API
- Function changed
- Remove the "Function calling" setting.
- Function calling is "disable" for conversation type "LLM"
- Function calling is "enable" for conversation type "Scenario/LLM"
- Remove the "Function calling" setting.
- Bug fixes
- The Azure TTS ApiKey setting is incorrect in the Voice settings.
- Lip-sync doesn't work properly with some character models.
- VRoidHub character model doesn't desplay when it's cache data is corrupted.
ver.3.4.1
[8-28-2024]
- Bug fixes (for Android)
- Unable to add music files to the initial music list.(musiclist0)
ver.3.4.0
[8-27-2024]
- Added functions
- Phone dial-out function
- Smartphone on-screen keyboard input button
- Start voice recognition with Bluetooth speaker play/pause button and headset hook button.
- Update SDK and libraries to the following.
- UniVRM 0.124.2
- Changed default model of ChatGPT to gpt-4o-mini.
- Other minor fixes
ver.3.3.1
[5-18-2024]
- Bug fix
- When the conversation type is "dialogue scenario only," there are cases in which the character does not learn properly.