Add Voice Input and Latest Release notes feed

Author: mythz

content/docs/features/meta.json

@@ -12,6 +12,7 @@
     "katex",
     "model-selector",
     "system-prompts",
-    "providers"
+    "providers",
+    "voice-input"
   ]
 }

content/docs/features/voice-input.mdx

@@ -0,0 +1,144 @@
+---
+title: Voice Input
+description: Adds voice-to-text transcription to the chat UI via a microphone button or ALT+D keyboard shortcut.
+---
+
+The [voice](https://github.com/ServiceStack/llms/tree/main/llms/extensions/voice) extension supports three transcription modes tried in order: `voxtype`, `transcribe`, and `voxtral-mini-latest`, using the first one that's available.
+
+To remove modes or change their priority, override with the `LLMS_VOICE` environment variable, e.g:
+
+```bash
+export LLMS_VOICE="transcribe,voxtral-mini-latest"
+```
+
+## Usage
+
+### 🎤 Microphone Button
+
+Click the microphone icon in the chat input area to start recording. Click again to stop and transcribe.
+
+
+If the **voice** extension is enabled the microphone button will appear in the chat input area, and the `ALT+D` keyboard shortcut will be available for voice input.
+
+### Keyboard Shortcut
+
+**Alt+D** toggles voice recording with two modes:
+
+- **Tap (< 500ms):** Toggle mode - starts recording, press again to stop
+- **Hold (≥ 500ms):** Push-to-talk - records **while held**, stops when released
+
+<Screenshot src="/img/features/voice-input.webp"  />
+
+The transcribed text is appended to the current message input. 
+
+<Screenshot src="/img/features/voice-recording.webp"  />
+
+Voice input can be disabled by [disabling the voice extension](/docs/configuration#disable-extensions) or by setting `LLMS_VOICE=""` to disable all modes.
+
+## Available Modes
+
+Voice Input will use the first available mode.
+
+## voxtype
+
+Uses the [voxtype.io](https://voxtype.io) CLI tool for local transcription.
+
+**Requirements:**
+- `voxtype` must be installed and on your `$PATH`
+- `ffmpeg` must be installed for audio format conversion
+
+#### Installation
+
+Voxtype works on GNOME, KDE, Sway, Hyprland, River—Wayland or X11 with [native packages](https://voxtype.io/#install) for **Arch Linux**, **Debian**, **Ubuntu**, **Fedora** and support for macOS via their source builds.
+
+## transcribe
+
+Use your preferred speech-to-text tool by creating a custom `transcribe` script or executable.
+
+**Requirements:**
+- A `transcribe` executable on your `$PATH` that accepts an audio wav file and outputs text to stdout
+- `ffmpeg` must be installed for audio format conversion
+
+**Interface:**
+
+```bash
+transcribe recording.wav > transcript.txt
+```
+
+See [Creating a transcribe Script](#creating-a-transcribe-script) for implementation examples.
+
+## voxtral-mini-latest
+
+Uses [Mistral's Voxtral model](https://docs.mistral.ai/models/voxtral-mini-transcribe-26-02) for cloud-based transcription. A good option if you want to avoid downloading a large model and using local CPU resources.
+
+**Requirements:**
+- Mistral provider must be enabled in your configuration
+- `MISTRAL_API_KEY` environment variable must be set
+
+**Pricing:** ~$0.003/minute
+
+---
+
+## Creating a transcribe Script
+
+Make the script executable and add it to your `$PATH`:
+
+```bash
+chmod +x ./transcribe
+sudo ln -s $(pwd)/transcribe /usr/local/bin/transcribe
+```
+
+### Using OpenAI Whisper
+
+Create a script using [uvx](https://github.com/astral-sh/uv) and [openai-whisper](https://github.com/openai/whisper):
+
+`./transcribe`
+
+```bash
+#!/usr/bin/env bash
+uvx --from openai-whisper whisper "$1" --model base.en --output_format txt --output_dir /tmp >/dev/null 2>&1
+
+BASENAME=$(basename "${1%.*}")
+cat "/tmp/${BASENAME}.txt"
+rm -f "/tmp/${BASENAME}.txt"
+```
+
+### Using Whisper.cpp
+
+[whisper.cpp](https://github.com/ggml-org/whisper.cpp) provides a faster, dependency-free C++ implementation.
+
+**Setup:**
+
+```bash
+git clone https://github.com/ggml-org/whisper.cpp.git
+cd whisper.cpp
+
+# Download a model
+sh ./models/download-ggml-model.sh base.en
+
+# Build
+cmake -B build
+cmake --build build -j --config Release
+
+# Test
+./build/bin/whisper-cli -f samples/jfk.wav
+```
+
+**Create the transcribe script:**
+
+`./transcribe`
+
+```bash
+#!/usr/bin/env bash
+SCRIPT_DIR="$(cd "$(dirname "$(readlink -f "${BASH_SOURCE[0]}")")" && pwd)"
+MODEL="$SCRIPT_DIR/models/ggml-base.en.bin"
+CLI="$SCRIPT_DIR/build/bin/whisper-cli"
+TMPFILE=$(mktemp /tmp/whisper-XXXXXX)
+
+trap 'rm -f "$TMPFILE" "${TMPFILE}.txt"' EXIT
+
+"$CLI" -m "$MODEL" -otxt -f "$1" -of "$TMPFILE" >/dev/null 2>&1
+
+cat "${TMPFILE}.txt"
+```
+

content/docs/getting-started/index.mdx

@@ -60,3 +60,13 @@ To update to the latest version:
 For Docker:
 
 <ShellCommand>docker pull ghcr.io/servicestack/llms:latest</ShellCommand>
+
+### Reset to latest configuration
+
+New versions sometimes include changes to `llms.json` config which isn't automatically updated. 
+
+To reset to the latest configuration just delete your `llms.json` and it will be recreated with the latest defaults on next run:
+
+```bash
+rm ~/.llms/llms.json
+```

content/docs/latest.mdx

@@ -0,0 +1,133 @@
+---
+title: Latest Features
+description: Latest features and updates in llms.py
+---
+
+## Feb 8, 2026
+
+### Support for Voice Input
+
+Added [Voice Input](/docs/features/voice-input) extension with speech-to-text transcription via a microphone button or `ALT+D` shortcut, supporting three modes: local transcription with **voxtype**, custom **transcribe** executable, and cloud-based **voxtral-mini-latest** via Mistral.
+
+<Screenshot src="/img/features/voice-recording.webp"  />
+
+- Added **tok/s** metrics in Chat UI on a per-message and per-thread basis
+
+## Feb 5, 2026
+
+### Voxtral Audio Models
+
+Added support for Mistral's [Voxtral audio transcription models](https://mistral.ai/news/voxtral-transcribe-2) - use the **audio** input filter in the model selector to find them.
+
+<Screenshot src="/img/models/voxtral-models.webp"  />
+
+Both the **Chat Completion** and dedicated **Audio Transcription** APIs deliver impressive speed, with the dedicated transcription endpoint returning results near-instantly.
+
+<ScreenshotsGallery className="mb-8" gridClass="grid grid-cols-1 md:grid-cols-2 gap-4" images={{
+    'Voxtral Chat': '/img/models/voxtrals-chat.webp',
+    'Voxtral Audio Transcription': '/img/models/voxtrals-audio-transcription.webp',
+}} />
+
+### Compact Threads
+
+Added [Compact Threads feature](/docs/features/chat-ui#compact-feature) for managing long conversations - it summarizes the current thread into a new, condensed thread targeting **30%** of the original context size. The compact button appears when a conversation exceeds **10 messages** or uses more than **40%** of the model's context limit. 
+
+<ScreenshotsGallery className="mb-8" gridClass="grid grid-cols-1 md:grid-cols-2 gap-4" images={{
+    'Compact Button': '/img/compact-button.webp',
+    'Compact Button Intensity': '/img/compact-intensity.webp',
+}} />
+
+The compaction model and prompts are fully customizable in `~/.llms/llms.json`.
+
+- Fix **OpenRouter** provider after [models.dev](https://models.dev) switched to use `@openrouter/ai-sdk-provider`. Remove `llms.json` to reset to default configuration:
+
+<ShellCommand>rm ~/.llms/llms.json</ShellCommand>
+
+## Feb 3, 2026
+
+- Removed duplicate filesystem tools from [Core Tools](/docs/features/core-tools), they're now only included in [File System Tools](/docs/features/core-tools#file-system-tools)
+
+- Add `sort_by` and `max_result` options in `search_files` and made `path` and optional parameter to improve utility and reduce tool use error rates. `path` now defaults to the first allowed directory (project dir).
+
+## Feb 3, 2026
+
+- Add support for overridable  **ClientTimeout** limits in `~/.llms/llms.json`:
+
+```json
+{
+    "limits": {
+        "client_timeout": 120
+    }
+}
+```
+
+- Show **proceed** button for assistant messages without content but with reasoning
+
+## Feb 2, 2026
+
+### Multi User Skills
+
+When Auth is enabled, each user [manages their own skill collection](/docs/extensions/skills#multi-user-skills) at `~/.llms/user/<user>/skills` and can enable or disable skills independently. Shared global & project-level skills remain accessible but read-only.
+
+## Jan 31, 2026
+
+- Refactor [GitHub Auth](/docs/deployment/github-oauth) out into a builtin [github_auth](https://github.com/ServiceStack/llms/tree/main/llms/extensions/github_auth) extension
+
+## Jan 30, 2026
+
+- Support for **tool calling** for models returned by local **Ollama** instances
+
+- New `openai-local` provider for custom OpenAI-compatible endpoints
+
+- Fix computer tool issues in Docker by only loading computer tool if run in environment with a display
+
+## Jan 29, 2026
+
+### Skills Management
+
+Added a full [Skills Management UI](/docs/extensions/skills) for creating, editing, and deleting skills directly from the browser. 
+
+Skills package domain-specific instructions, scripts, references & assets that enhance your AI agent.
+
+<Screenshot src="/img/skills/skills-edit-page.webp"  />
+
+### Browse & Install Skills
+
+Added a [Skill Browser](/docs/extensions/skills#browsing-and-installing-skills) with access to the top 5,000 community skills from [skills.sh](http://skills.sh). Search, browse, and install pre-built skills directly into your personal collection.
+
+<ScreenshotsGallery className="mb-8" gridClass="grid grid-cols-1 md:grid-cols-2 gap-4" images={{
+    'Browse Skills': '/img/skills/skills-browse.webp',
+    'Installing Skill': '/img/skills/skills-installing.webp',
+}} />
+
+## Jan 28, 2026
+
+- Use a barebones fallback markdown render when [markdown renders like KaTex](/docs/features/katex) fail
+
+- Use `sanitizeHtml` to avoid breaking layout when displaying rendered html
+
+## Jan 26, 2026
+
+- Add copy button to **TextViewer** popover menu
+
+- Add **proceed** and **retry** buttons at the bottom of Threads to continue agent loop
+
+- Add [filesystem tools](/docs/features/core-tools#file-system-tools) in [computer](/docs/extensions/computer_use) extension
+
+- Add a simple `sendUserMessage` API in UI to simulate a new user message on the thread
+
+- Implement `TextViewer` component for displaying Tool Args, Tool Output + SystemPrompt
+
+## Jan 24, 2026
+
+- Auto collapse long tool args content and add ability to min/maximize text content
+
+## Jan 23, 2026
+
+- Add built-in [computer_use extension](/docs/extensions/computer_use)
+
+---
+
+## v3 Released
+
+See [v3 release notes](/docs/v3) for details on the major new features and improvements in v3.

content/docs/meta.json

@@ -2,6 +2,7 @@
   "title": "Documentation",
   "pages": [
     "index",
+    "latest",
     "v3",
     "getting-started",
     "features",