v0.12.0-beta.5
multica-ai/multicav0.12.0-beta.5Aug 29, 2026by nekomeowww
Upgrading?
AI Summary
This beta release introduces the MAGIC driver for Live2D to generate Neuro-sama-like motion, adds support for VOICEVOX and AivisSpeech as local speech providers, and improves Live2D import reporting and macOS compatibility. It also includes fixes for chat session reliability, mobile UI positioning, and desktop local server startup issues.
Key Highlights
- New MAGIC driver for Live2D to generate Neuro-sama-like motion.
- Support for VOICEVOX and AivisSpeech as local speech providers.
- Improved Live2D import reporting and macOS ZIP archive support.
- Fixed chat session restoration and mobile chat history positioning.
- Reliable desktop local server startup across Windows and macOS.
New Features
- MAGIC driver for Live2D with bundled Idle/Calming and Speaking/Excited profiles.
- VOICEVOX Engine integration as a local speech provider with connection and voice controls.
- AivisSpeech Engine integration as a local speech provider with connection and voice controls.
- Live2D Motion Control workbench supports recording, editing, playback, and procedural motion generation.
- New PlayStation 5 DualSense USB and Bluetooth support via internal gamepad packages.
Full Release Notes
## v0.12.0-beta.5 Highlights ## New Contributors * @nayounsang made their first contribution in https://github.com/moeru-ai/airi/pull/2404 ### Product updates #### Live2D - You can now select the MAGIC[^1] driver to generate Neuro-sama like motion (aka Neuro bump). - The driver includes bundled Idle / calm and Speaking / excited profiles. It can preserve speech lip sync and keep the character looking forward. - Live2D imports now show a clear report before import. It lists model data, absent references, unreferenced resources, and steps to fix each issue. - Live2D ZIP archives created on macOS now import correctly. Hidden metadata no longer prevents the importer from finding model files and expressions. #### Speech - You can now use VOICEVOX Engine or AivisSpeech Engine as a local speech provider. Each provider includes connection and voice controls. ### Bug fixes and polish - Chat now reliably creates or restores a session during startup in single-window and multi-window setups. - Short mobile chat histories now sit above the composer. New messages stay near the bottom, while upward scrolling keeps your reading position. - Chat, settings, onboarding, and other panels now use consistent scroll areas. On desktop, the chat composer remains fixed while the history scrolls. - On iOS, microphone access now opens the system permission prompt instead of closing the app. The app remains open after you deny access. - The desktop local server now starts reliably on Windows and macOS. Socket setup no longer requests unsupported port reuse. - The desktop title bar no longer shows an inactive information icon. ### To developers - @proj-airi/server-runtime now gives each port to one listener and disables reusePort. This prevents unsupported socket errors across desktop platforms. ### To contributors - New internal gamepad packages normalize browser controllers, provide Vue lifecycle integration, and add PlayStation 5 DualSense USB and Bluetooth support. - The Live2D Motion Control workbench now supports recording, editing, playback, filtering, keyboard and controller input, and procedural motion generation. - Fresh Electron 42 setups now install Electron before dev or start, so the desktop app no longer fails before launch. - The retired transcription package and its stale CI command are gone. Nix dependency hashes and the documented typecheck command are now current. [^1]: ~~MAGIC stands for Markovian Animation Generator with Illusory Conditioning~~ **Full Changelog**: https://github.com/moeru-ai/airi/compare/v0.12.0-beta.4...v0.12.0-beta.5
Related Repositories
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
The world’s fastest framework for building websites.
:cherry_blossom: A command-line fuzzy finder