{"id":11673,"date":"2026-11-17T11:00:23","date_gmt":"2026-11-17T02:00:23","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/?p=11673"},"modified":"2026-11-17T11:09:35","modified_gmt":"2026-11-17T02:09:35","slug":"open-webui-v012-1-released","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/open-webui-v012-1-released\/","title":{"rendered":"Open WebUI v0.12.1 Released: External Apps and More"},"content":{"rendered":"<p><!-- lmw:facts --><\/p>\n<h2>At a Glance<\/h2>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Item<\/th>\n<th>Value<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Repository<\/td>\n<td><a href=\"https:\/\/github.com\/open-webui\/open-webui\">open-webui\/open-webui<\/a><\/td>\n<\/tr>\n<tr>\n<td>Version<\/td>\n<td><a href=\"https:\/\/github.com\/open-webui\/open-webui\/releases\/tag\/v0.12.1\">v0.12.1<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-10-15<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>NOASSERTION<\/td>\n<\/tr>\n<tr>\n<td>Source type<\/td>\n<td>Primary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>Values determined by this site&#8217;s code when the information was collected. Dates are JST.<\/em><\/p>\n<p><!-- \/lmw:facts --><\/p>\n<h2>Overview<\/h2>\n<p>Open WebUI v0.12.1 has been released. Open WebUI is a Python-based, user-friendly AI interface that allows users to utilize various models such as Ollama and the OpenAI API as a backend. It is provided under the NOASSERTION license.<\/p>\n<p>The most significant change in this update is the introduction of the &#8220;External apps&#8221; integration feature within channels. This allows administrators to add permitted external applications to channels and have them interact via @mentions. For existing users, this significantly improves convenience as a chatbot, making the update worth considering.<\/p>\n<h2>Key Changes<\/h2>\n<h3>External App Integration in Channels<\/h3>\n<p>Administrators can now enable the app feature using &#8220;Admin Settings &gt; General&#8221; or the environment variable <code>ENABLE_APPS<\/code>. External apps are connected via HTTPS addresses, and administrators can individually review and approve permissions such as reading and posting messages. Once a channel manager adds an app as a member, users can receive responses from the app by typing <code>@appname<\/code> and sending a mention in the chat. Apps on private networks can also be connected via HTTP by listing them in <code>APP_ALLOWED_PRIVATE_ORIGINS<\/code>.<\/p>\n<h3>Revision Comparison and Merge Features<\/h3>\n<p>A &#8220;Compare revision&#8221; button has been added to skill file editing, prompt editing, and system prompts within the model editor. It is also accessible from the &#8220;+&#8221; menu in the chat input box and the <code>\/compare<\/code> command. This allows users to compare model-generated proposals side-by-side with the current content, reviewing and applying changes one by one. The terminal-style file browser also allows users to select two files and open a similar comparison view.<\/p>\n<h3>Azure OpenAI Realtime Support<\/h3>\n<p>Azure OpenAI can now be selected as a provider in the Realtime mode for voice calls. Administrators can specify Azure OpenAI in the &#8220;Voice calls&#8221; section of the audio settings, input the endpoint and deployment name, and authenticate using an API key or Microsoft Entra ID. In connection with this, the environment variables <code>AUDIO_REALTIME_PROVIDER<\/code> and <code>AUDIO_REALTIME_AUTH_TYPE<\/code> have also been newly added.<\/p>\n<h3>Enhanced Analytics Dashboard<\/h3>\n<p>The analytics screen, which allows users to check usage status, has been improved. Usage status by model and activity by user can now be switched and displayed in a single table, with input tokens, output tokens, and total tokens displayed as separate columns. Previously, there was only a single &#8220;Tokens&#8221; column, but now detailed breakdowns can be sorted and viewed column by column.<\/p>\n<h3>Faster Search and Voice Call Improvements<\/h3>\n<p>Single-word searches in chat history have been made about 40% faster. This is due to optimizing the check count for each chat from twice to once. Additionally, model avatars are now displayed in the &#8220;Standard&#8221; mode of voice calls, and support for gestures when using native function calling has been added. Improvements have also been made to prevent the screen from sleeping during calls in Realtime mode.<\/p>\n<h3>Important Bug Fixes<\/h3>\n<p>Several important bug fixes for local environments are included. First, an issue where the skill editor and other features failed to work with a <code>crypto.randomUUID<\/code> error when accessed via plain HTTP has been fixed. Additionally, a problem where reasons or comments entered when submitting feedback (such as thumbs down) disappeared at the timing of tag generation has been resolved. The behavior where unrelated file previews closed when deleting a folder in the knowledge base has also been fixed.<\/p>\n<h2>Specifications<\/h2>\n<p>With the enhancement of voice dialogue features, the supported model providers and avatar formats have been expanded in this version.<\/p>\n<p>First, the Realtime API of Azure OpenAI is newly supported as a backend model. This enables low-latency voice calls through models deployed in Azure environments, in addition to OpenAI&#8217;s native API. Administrators can configure this by selecting Azure OpenAI as the provider in the &#8220;Voice calls&#8221; section of the audio settings and entering the endpoint and deployment name. As for the authentication method, Microsoft Entra ID is available in addition to traditional API keys. Related to this, the environment variables <code>AUDIO_REALTIME_PROVIDER<\/code> and <code>AUDIO_REALTIME_AUTH_TYPE<\/code> have been newly introduced, facilitating configuration from container environments.<\/p>\n<p>In terms of Text-to-Speech (TTS), &#8220;Kokoro.js (Browser)&#8221; running on the browser is now supported. In environments where a speech synthesis engine is not built on the server side, users can select this voice from their user settings to enable voice responses utilizing the browser&#8217;s computational resources. This allows users to enjoy high-quality voice dialogue in a local environment while keeping server load low.<\/p>\n<p>As for the visual interface, support for VRM 0.x format 3D avatars has been improved. Previously, issues existed such as the avatar&#8217;s arms remaining unnaturally raised or idle movements being horizontally flipped, but in this version, the rest pose with lowered arms is correctly applied, and breathing and swaying movements have been corrected to be more natural. Furthermore, operations such as rotating the avatar by dragging or zooming with the mouse wheel are now possible during voice calls or in the model editor preview.<\/p>\n<p>Regarding hardware support, CUDA acceleration using NVIDIA GPU and CPU-only operation continue to be supported. Particularly when using Docker, optimal performance can be obtained by selecting tags such as <code>:cuda<\/code> (for GPU), <code>:ollama<\/code> (bundled with Ollama), or <code>:main<\/code> (standard version) according to the user&#8217;s hardware configuration.<\/p>\n<h2>How to Get It<\/h2>\n<p>Open WebUI update procedures vary depending on the current installation method. Based on the provided installation guides, representative procedures are shown below.<\/p>\n<p><strong>When installing using Python pip<\/strong> After confirming that you are using a Python 3.11 environment, run the following command in the terminal to update the package to the latest version:<\/p>\n<pre><code class=\"language-bash\">pip install open-webui\n<\/code><\/pre>\n<p>Once the update is complete, restart the server with the following command:<\/p>\n<pre><code class=\"language-bash\">open-webui serve\n<\/code><\/pre>\n<p><strong>When installing using Docker<\/strong> In a Docker environment, the update is completed by pulling the latest image and restarting the container. To prevent data loss, make sure to mount the volume using the <code>-v open-webui:\/app\/backend\/data<\/code> option.<\/p>\n<p>The standard startup command when Ollama is running on the same computer is as follows:<\/p>\n<pre><code class=\"language-bash\">docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:\/app\/backend\/data --name open-webui --restart always ghcr.io\/open-webui\/open-webui:main\n<\/code><\/pre>\n<p>When using an NVIDIA GPU (CUDA), use the following command:<\/p>\n<pre><code class=\"language-bash\">docker run -d -p 3000:8080 --gpus all --add-host=host.docker.internal:host-gateway -v open-webui:\/app\/backend\/data --name open-webui --restart always ghcr.io\/open-webui\/open-webui:cuda\n<\/code><\/pre>\n<p>Also, if you want to use Ollama bundled inside the container, the following command (GPU-supported version) is available:<\/p>\n<pre><code class=\"language-bash\">docker run -d -p 3000:8080 --gpus=all -v ollama:\/root\/.ollama -v open-webui:\/app\/backend\/data --name open-webui --restart always ghcr.io\/open-webui\/open-webui:ollama\n<\/code><\/pre>\n<p>If an existing container is running, run <code>docker stop open-webui<\/code> and <code>docker rm open-webui<\/code> to remove the old container, then start a container based on the new image using the commands above.<\/p>\n<p><!-- lmw:related --><\/p>\n<h2>Related Articles<\/h2>\n<ul>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/open-webui-v0131-release\/\">Open WebUI v0.13.1 Released with Security Fixes and Tether<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/open-webui-v0-13-0\/\">Open WebUI v0.13.0 Released: Tabbed Workspaces &amp; Security Fixes<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/open-webui-v0-12-3-released\/\">Open WebUI v0.12.3 Released with E2EE Chats and Redis Streaming<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/open-webui-v0125-released\/\">Open WebUI v0.12.5 Released with Security Patches and Multi-Page Notes<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:related --><\/p>\n<p><!-- lmw:next-steps --><\/p>\n<h2>What to Read Next<\/h2>\n<ul>\n<li><strong>Follow this tool<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-open-webui-en\/\">Open WebUI overview and release history (181 releases tracked)<\/a><\/li>\n<li><strong>Other uis and desktop apps<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-jan-en\/\">Jan<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-text-generation-webui-en\/\">TextGen<\/a><\/li>\n<li><strong>Engines mentioned in this article<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-ollama-en\/\">Ollama<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:next-steps --><\/p>\n<h2>Sources<\/h2>\n<ul>\n<li><a href=\"https:\/\/github.com\/open-webui\/open-webui\/releases\/tag\/v0.12.1\">https:\/\/github.com\/open-webui\/open-webui\/releases\/tag\/v0.12.1<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/open-webui\/open-webui\/pull\/32378\">https:\/\/github.com\/open-webui\/open-webui\/pull\/32378<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/open-webui\/open-webui\/pull\/32343\">https:\/\/github.com\/open-webui\/open-webui\/pull\/32343<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/open-webui\/open-webui\/pull\/32270\">https:\/\/github.com\/open-webui\/open-webui\/pull\/32270<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/open-webui\/open-webui\/pull\/32328\">https:\/\/github.com\/open-webui\/open-webui\/pull\/32328<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/open-webui\/open-webui\/pull\/32334\">https:\/\/github.com\/open-webui\/open-webui\/pull\/32334<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/open-webui\/open-webui\/pull\/32319\">https:\/\/github.com\/open-webui\/open-webui\/pull\/32319<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/open-webui\/open-webui\/pull\/32321\">https:\/\/github.com\/open-webui\/open-webui\/pull\/32321<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Open WebUI v0.12.1 is now available, featuring external app integration in channels, Azure OpenAI Realtime support, and various improvements.<\/p>\n","protected":false},"author":1,"featured_media":11672,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[105],"tags":[3346,3348,1475,1093,1917,1547],"class_list":["post-11673","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-engines-and-tools","tag-ai-interface-en","tag-azure-openai-en","tag-docker-en","tag-ollama-en","tag-open-webui-en","tag-verified"],"lang":"en","translations":{"en":11673,"ja":11671},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11673","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/comments?post=11673"}],"version-history":[{"count":2,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11673\/revisions"}],"predecessor-version":[{"id":17781,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11673\/revisions\/17781"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/11672"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=11673"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=11673"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=11673"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}