# AIRI v0.12.0-beta.1 - Product: AIRI (https://whatsnew.fyi/product/airi) - Vendor: AIRI - Date: 2026-08-24 - Version: v0.12.0-beta.1 - Original notes: https://github.com/moeru-ai/airi/releases/tag/v0.12.0-beta.1 - Permalink: https://whatsnew.fyi/product/airi/releases/v0.12.0-beta.1 - Labels: Pre-release What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog. Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'. --- - **added** — Desktop version now supports MMD models with motion import and adjustment of physics, gaze, lip sync, expressions, and materials - **added** — Desktop version now supports Tachie archives that switch complete character images to match emotions - **added** — VRM characters now react when you click their heads, arms, hands, or feet - **added** — New Hearing playground lets you monitor the active speech-recognition pipeline and review each completed speech segment - **added** — Desktop version can relay conversations to a connected Minecraft bot and read supported bot speech aloud - **added** — Mobile version now has a permission panel and clearer onboarding - **added** — Android microphone selection is now available on mobile - **added** — You can enable Thinking for supported Consciousness models from one model option - **added** — Steam sign-in and account linking are now available - **added** — Hosted authentication now supports Apple sign-in and native Apple ID tokens - **changed** — Live2D imports now support CJK paths and older filename encodings - **changed** — You can now mute voice output across sessions or stop all current speech from the Controls Island - **changed** — Speech recognition now keeps transcript corrections and handles voice activity, pauses, and streaming audio more reliably - **changed** — Long conversations use less rendering work so chat remains responsive as the history grows - **changed** — Tool messages now remain available across chat turns - **changed** — Streamed messages no longer flash and tool-call progress stays synchronized - **changed** — Chat math now uses consistent syntax for predictable display - **changed** — The Controls Island now moves to the nearest window corner after you reposition the desktop window - **changed** — Connection status now lives inside the Controls Island - **changed** — Desktop pairing settings and QR codes now stay synchronized - **changed** — Mobile browsers no longer have the software keyboard hide or shift the chat input unexpectedly - **changed** — DeepSeek now applies its reasoning mode correctly - **changed** — Provider validation status now persists and each provider uses its own validation rules - **changed** — Tool use works with more providers because AIRI adapts tool schemas to each provider - **changed** — Volcengine Coding Plan now lists current models with localized descriptions - **changed** — Account deletion now revokes linked social authorizations - **changed** — Hosted model routing can fall back across configured provider groups when one route is unavailable - **changed** — AIRI now starts on Linux ARM64 and Flatpak installs include desktop and AppStream metadata - **fixed** — A provider settings loop could leave AIRI loading forever; the startup and synchronization path is now stable - **fixed** — Desktop chat creation, switching, deletion, and import refresh now work reliably - **fixed** — Chat and sign-in state now remain consistent across Electron windows - **fixed** — AIRI Card drafts, active sessions, avatar Models, and runtime data now remain intact during edits and activation - **fixed** — Whisper worker errors now stop promptly instead of leaving transcription stuck - **fixed** — Stopping Kokoro speech no longer destroys the worker needed for the next response - **fixed** — Safari no longer blocks the authentication interface while it loads code chunks - **fixed** — If a Live2D model fails to render, the Stage now shows a clear error and remains usable ##### v0.12.0-beta.1 Highlights This beta adds new character formats, stronger desktop controls, and major reliability work across chat, speech recognition, and provider settings. ##### New Contributors * @ricemaster1 made their first contribution in https://github.com/moeru-ai/airi/pull/2016 * @juyua9 made their first contribution in https://github.com/moeru-ai/airi/pull/1803 * @wuyua9 made their first contribution in https://github.com/moeru-ai/airi/pull/1911 * @Anfi1 made their first contribution in https://github.com/moeru-ai/airi/pull/2072 * @ShiroKSH made their first contribution in https://github.com/moeru-ai/airi/pull/2054 * @kobihikri made their first contribution in https://github.com/moeru-ai/airi/pull/2149 * @vuyua9 made their first contribution in https://github.com/moeru-ai/airi/pull/1871 * @LauraGPT made their first contribution in https://github.com/moeru-ai/airi/pull/2207 * @MilkyWeighW made their first contribution in https://github.com/moeru-ai/airi/pull/2205 * @ztcools made their first contribution in https://github.com/moeru-ai/airi/pull/2178 * @xianjianlf2 made their first contribution in https://github.com/moeru-ai/airi/pull/2280 * @yzxcj797 made their first contribution in https://github.com/moeru-ai/airi/pull/2300 * @ppdbxdawj made their first contribution in https://github.com/moeru-ai/airi/pull/2321 ###### Product updates ###### Models and Stage - Desktop ver. now supports MMD models. You can import motions and adjust physics, gaze, lip sync, expressions, and materials. - Desktop ver. now supports Tachie archives that switch complete character images to match emotions. - VRM characters now react when you click their heads, arms, hands, or feet. - Live2D imports now support CJK paths and older filename encodings. - If a Live2D model fails to render, the Stage now shows a clear error and remains usable. ###### Chat, Hearing, and Speech - You can now mute voice output across sessions or stop all current speech from the Controls Island. - The new Hearing playground lets you monitor the active speech-recognition pipeline and review each completed speech segment. - Speech recognition now keeps transcript corrections and handles voice activity, pauses, and streaming audio more reliably. - Long conversations use less rendering work, so chat remains responsive as the history grows. - Tool messages now remain available across chat turns. - Streamed messages no longer flash, and tool-call progress stays synchronized. - Chat math now uses consistent syntax for predictable display. ###### Desktop and Mobile - The Controls Island now moves to the nearest window corner after you reposition the desktop window. - Connection status now lives inside the Controls Island, and tray-based window moves use animations. - Desktop pairing settings and QR codes now stay synchronized. - Desktop ver. can relay conversations to a connected Minecraft bot and read supported bot speech aloud. - AIRI now starts on Linux ARM64. Flatpak installs also include desktop and AppStream metadata. - Mobile ver. now has a permission panel, clearer onboarding, and Android microphone selection. - On mobile browsers, the software keyboard no longer hides or shifts the chat input unexpectedly. ###### Accounts and providers - You can enable Thinking for supported Consciousness models from one model option. - DeepSeek now applies its reasoning mode correctly. - Provider validation status now persists, and each provider uses its own validation rules. - Tool use works with more providers because AIRI adapts tool schemas to each provider. - Volcengine Coding Plan now lists current models with localized descriptions. - Steam sign-in and account linking are now available. - Hosted authentication now supports Apple sign-in and native Apple ID tokens. - Account deletion now revokes linked social authorizations. - Hosted model routing can fall back across configured provider groups when one _[Truncated at 4000 characters — full notes: https://github.com/moeru-ai/airi/releases/tag/v0.12.0-beta.1]_