# Open WebUI v0.6.12 — Release & Upgrade Intelligence
- **Product:** Open WebUI (https://openwebui.com)
- **Version:** v0.6.12
- **Released:** May 28, 2025
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/open-webui/updates/v0.6.12/

## Executive Summary (TL;DR)
Open WebUI v0.6.12. Source highlight: [0.6.12] - 2025-05-29

## New Features
- 🧩 **Custom Advanced Model Parameters**: You can now add your own tailor-made advanced parameters to any model, empowering you to fine-tune behavior and unlock greater flexibility beyond just the built-in options—accelerate your experimentation.
- 🪧 **Datalab Marker API Content Extraction Support**: Seamlessly extract content from files and documents using the Datalab Marker API directly in your workflows, enabling more robust structured data extraction for RAG and document processing with just a simple engine switch in the UI.
- ⚡ **Parallelized Base Model Fetching**: Experience noticeably faster startup and model refresh times—base model data now loads in parallel, drastically shortening delays in busy or large-scale deployments.
- 🧠 **Efficient Function Loading and Caching**: Functions are now only reloaded if their content changes, preventing unnecessary duplicate loads, saving bandwidth, and boosting performance.
- 🌍 **Localization & Translation Enhancements**: Improved and expanded Simplified, Traditional Chinese, and Russian translations, providing smoother, more accurate, and context-aware experiences for global users.

## Improvements
- 🧹 **Duplicate CSS Elements**: Streamlined the UI by removing redundant CSS, reducing clutter and improving load times for a smoother visual experience.

## Bug Fixes
- 💬 **Stable Message Input Box**: Fixed an issue where the message input box would shift unexpectedly (especially on mobile or with screen reader support), ensuring a smooth and reliable typing experience for every user.
- 🔊 **Reliable Read Aloud (Text-to-Speech)**: Read aloud now works seamlessly across messages, so users depending on TTS for accessibility or multitasking will experience uninterrupted and clear voice playback.
- 🖼 **Image Preview and Download Restored**: Fixed problems with image preview and downloads, ensuring frictionless creation, previewing, and downloading of images in your chats—no more interruptions in creative or documentation workflows.
- 📱 **Improved Mobile Styling for Workspace Capabilities**: Capabilities management is now readable and easy-to-use even on mobile devices, empowering admins and users to manage access quickly on the go.
- 🔁 **/api/v1/retrieval/query/collection Endpoint Reliability**: Queries to retrieval collections now return the expected results, bolstering the reliability of your knowledge workflows and citation-ready responses.