Set Up OpenRouter AI Markdown Editor Graph Builder MathPix Image Describer Ally Reporting Local Chat Chat

MathJax Loaded: No

Set Up

Status Summary

OpenRouter OpenRouter: Checking...
MathPix MathPix: Checking...
Microsoft Foundry Microsoft Foundry: Checking...
Ally Ally: Checking...
Local AI Models Local AI Models: Checking...

Quick Start Guide

This application provides six tools for accessible content creation. Most tools require an API credential to function. Expand a section below to configure your credentials.

Set Up: This page. Configure API credentials for every tool, and download or remove local AI models. No credentials needed.
OpenRouter AI: Send prompts to a wide range of AI models. Requires an OpenRouter API key.
Microsoft Foundry: Alternative provider for AI tools, using Microsoft AI models via your own proxy. Requires deploying a Cloudflare Worker.
Markdown Editor: Write and preview Markdown with support for charts, diagrams, and mathematics. No credentials needed.
Graph Builder: Create accessible charts and graphs with data tables and alt text. No credentials needed.
MathPix: Convert images of handwritten or printed mathematics into LaTeX. Requires a MathPix App ID and App Key.
Image Describer: Generate detailed alt text for images using AI. Requires an OpenRouter API key, or download a local model below.
Chat: Hold a conversation with a wide range of cloud AI models, filtering them by cost, capability and provider. Requires an OpenRouter API key, or a Microsoft Foundry connection.
Local Chat: Chat with a local AI model running entirely in your browser. No data leaves your device. No credentials needed, but you will need to download a model from the Local AI Models section.
Ally Reporting: Query the Blackboard Ally API for course accessibility reports. Requires an Ally API token and Client ID.

API Credentials

Active Provider

OpenRouter

Microsoft Foundry

University sign-in

Some tools can use University of Southampton AI services. Select the button to sign in. Signing in shows that you are a University of Southampton member. You will be brought back here straight afterwards.

Save anything you have typed on this page before you sign in, because moving to Microsoft will clear it.

OpenRouter Not configured

OpenRouter API Key

Your API key is stored locally in your browser and is never sent to any server other than OpenRouter.

MathPix Not configured

App ID

App Key

Your MathPix credentials are stored locally in your browser. Get your App ID and Key from the MathPix dashboard (opens in new tab).

Microsoft Foundry Not configured

Cloudflare Worker Proxy URL

User token (optional)

Microsoft Foundry provides Azure-hosted AI models through a Cloudflare Worker proxy. The proxy URL is required.

Leave the user token empty unless you have been given one. Most proxies identify you through the University sign-in card instead. The token field is for the older shared-token arrangement, and filling it in will not sign you in. Anything you enter is stored locally in your browser.

Ally Not configured

Region

Select the region that matches your Ally instance. EU is the default for most institutions.

Client ID

API Token

Your Ally credentials are stored locally in your browser. Find your Client ID and token in the Ally Institutional Report.

Proxy Worker URL (alternative to an API token)

A proxy worker holds the Ally token for you, so you can use Ally Reporting without entering one here. You still need a Client ID and region. Enter either an API token or a worker URL — if you provide both, the token is used. This URL is not a secret, so unticking Remember credentials keeps it. Clearing your credentials removes it, and so does emptying this box and selecting Save Credentials.

Remember credentials in this browser

When unchecked, all Ally credentials will be removed from your browser storage.

To test your Ally connection, use the Test Connection button in the Ally Reporting tool.

Local AI Models

Download and manage AI models that run locally in your browser. These models work without an API key after initial download.

Description Generation

Generate image descriptions locally — no API key or internet connection required after initial download.

Choose which local model to use for generation in the Image Describer tool. Download models here, then select your preferred model when generating descriptions.

FastVLM 0.5B Local description generation (no API key needed)

~350 MB

Checking…

Qwen3.5-0.8B Structured local descriptions

~1,000 MB

Checking…

LFM2-VL 450M Compact local descriptions (no API key needed)

~349 MB

Checking…

Analysis Pipeline

CLIP ViT-B/32 Zero-shot image classification

~151 MB

Checking…

Florence-2 Captioning, object detection, OCR

~200 MB

Checking…

Depth Anything V2 Monocular depth estimation

~50 MB

Checking…

Florence-2 enhancement (AI caption and supplementary OCR) is available when using the Image Describer tool with an uploaded image.

Text Generation

Local text models for chat and AI tasks — no API key or internet connection required after initial download.

LFM2 350M Fastest model — works on all hardware including integrated GPUs

~284 MB

Checking…

Details & benchmarks

Strengths
Limitations
Best for

Hardware	Speed	Context safe	Rating

LFM2.5 1.2B Instruct Recommended for discrete GPUs — instruct-tuned, 128K context

~836 MB

Checking…

Details & benchmarks

Strengths
Limitations
Best for

Hardware	Speed	Context safe	Rating

Phi 3.5 Mini Highest quality ONNX model — requires 8 GB+ discrete GPU

~2,300 MB

Checking…

Details & benchmarks

Strengths
Limitations
Best for

Hardware	Speed	Context safe	Rating

Llama 3.2 1B Best balance of speed and quality via WebLLM — works on all GPUs

~879 MB

Checking…

Details & benchmarks

Strengths
Limitations
Best for

Hardware	Speed	Context safe	Rating

Qwen 2.5 1.5B WebLLM mid-tier — better quality than 1B, works on all GPUs

~1,500 MB

Checking…

Details & benchmarks

Strengths
Limitations
Best for

Hardware	Speed	Context safe	Rating

Llama 3.2 3B Highest quality with full context — works on 4 GB+ GPUs

~1,724 MB

Checking…

Details & benchmarks

Strengths
Limitations
Best for

Hardware	Speed	Context safe	Rating

Text-to-Speech

Supertonic TTS Natural-sounding speech — read alt text aloud with near-human quality

~263 MB

Checking…

Voice Settings

Voice type

Browser voice (instant, no download) Natural voice (requires download)

Voice

Speed: 1.0×

Announce structure (headings, lists, tables)

When enabled, Read Aloud announces structural cues such as "Heading level 2" and "Bulleted list with 3 items" to help you understand the layout of the content.

Code blocks

Choose how code blocks are read aloud. "Summarise with first line" announces the language, line count, and the first non-blank line. "Summarise" announces only the language and line count. "Read all code" reads every character, including punctuation.

GPU Memory

No models loaded in GPU memory

Storage & Cache

Storage: checking…

Checking cache…

Loaded (in memory) Cached (on disk) Not downloaded Downloading…

OpenRouter Testing

Select an AI Model:

Select a model to view detailed information about its capabilities, pricing, and features.

Advanced Model Filters Showing all models

Loading models...

Enter your prompt:

Choose file or drag here Images & PDFs supported

Supported: Images (JPG, PNG, WebP) up to 20MB, PDFs up to 512MB

Response Streaming Options

No Streaming Wait for complete response before displaying formatted content Standard Streaming Show response as plain text while generating, format when complete

System Instructions

Provide context and instructions for how the AI should behave.

Response Creativity (Temperature) Current: 0.8

Focused (0.0) Balanced (1.0) Creative (2.0)

Controls response creativity. Lower values give focused, consistent responses. Higher values increase variety and creativity.

Response Diversity (Top P) Current: 1.0

Focused (0.1) Balanced (0.5) Varied (1.0)

Adjusts how varied the model's word choices can be.

Maximum Response Length Current: 1024 tokens

/ 4096 available

Short Medium Long

Controls maximum length of AI responses. Longer responses cost more tokens.

Response Variety (Repetition Control) Current: Balanced (0.0, 0.0)

Word Variety

More Similar Balanced More Varied

Word variety: 0.0

Phrase Variety

More Similar Balanced More Varied

Phrase variety: 0.0

Controls how varied the AI's word and phrase choices will be. Higher values create more diverse language, while lower values allow more repetition. Values below 0 encourage repetition, which can be useful for maintaining consistency.

Status

Updates

00:00.000 Ready

Results

OpenRouter API Configuration

Manage all API credentials in Set Up

Developer Information

API Credits Remaining:

...

Last Transaction Cost:

...

Provider Information:

...

Request Timing:

...

Finish Reason:

...

Prompt Tokens:

...

Completion Tokens:

...

Token Efficiency:

...

Model Changes:

None

Request:

...

Response:

...

Dependency Analysis

Markdown converter

Instructions

Keyboard Shortcuts

Ctrl + Enter - Render markdown
Esc - Clear editor
? - Show/hide shortcuts

These controls only work while the textbox is active.

Creating charts

Chart.js is supported.


                ```chart
                {
                  "type": "line",
                  "data": {
                    "labels": ["January", "February", "March", "April", "May", "June", "July"],
                    "datasets": [{
                      "label": "Monthly Sales",
                      "data": [65, 59, 80, 81, 56, 55, 40],
                      "fill": false,
                      "tension": 0.1
                    }]
                  }
                }
                ```

Custom Chart Descriptions

You can provide your own custom descriptions for charts by adding a `descriptions` object within your chart configuration:


"descriptions": {
    "short": "Your concise chart description here.",
    "detailed": "Your detailed HTML description here. You can use paragraphs, lists, and other HTML elements."
  }

Creating charts

Chart.js is supported.


                ```chart
                {
                  "type": "line",
                  "data": {
                    "labels": ["January", "February", "March", "April", "May", "June", "July"],
                    "datasets": [{
                      "label": "Monthly Sales",
                      "data": [65, 59, 80, 81, 56, 55, 40],
                      "fill": false,
                      "tension": 0.1
                    }]
                  }
                }
                ```

Creating diagrams

Mermaid is supported.


                ```mermaid
                graph TB
                    A[Start] --> B{Is it raining?}
                    B -->|Yes| C[Take umbrella]
                    B -->|No| D[Take sunglasses]
                    C --> E[Go out]
                    D --> E
                    E --> F[Return home]
                ```

Enter Markdown text. LaTeX math, charts and mermaid supported:

Load an example:
Examples demonstrate various markdown features including tables, charts, and diagrams.

HTML Output:

Graph Builder

Step 1 of 4: Add your data
2 Choose Chart Step 2 of 4: Choose your chart type
3 Configure Step 3 of 4: Configure your chart
4 Complete Step 4 of 4: Your chart is complete

Step 1: Add Your Data

How would you like to add your data?

Enter your data row by row

Paste your CSV data

Paste CSV data here:

Paste data with headers in the first row. Use commas to separate values.

Example:

Category,Value
Mathematics,85
English,72
Science,91

Upload a CSV file

📁 Select a CSV file

Select a CSV file from your computer or drag and drop one into the box above. Maximum file size: 1MB.

Step 2: Choose Chart Type

Step 3: Configure Your Chart

Live Preview

Chart Settings

Chart Title:

X-Axis Label:

Y-Axis Label:

Show Legend

Show Grid Lines

Stack series

✓ Your Chart is Ready!

Your accessible chart has been created with all the features you need.

MathPix Mathematics OCR

Upload File Draw Mathematics Camera Capture Convert MMD Resume Session

MathPix Server:: European Union
Use content for training:: No

Upload Mathematics

Drop file here, or select to browse.
Supports: Images (JPEG, PNG, WebP), Documents (PDF, DOCX, PPTX)

Quick tip: You can paste images directly from your clipboard (Ctrl+V or Cmd+V)

Draw your mathematical expression using your mouse or touch input. The system will recognise handwritten mathematics.

Alternative: Drawing is only supported using stylus / mouse / touchpad / touch or other pointing devices. For other modes of input, please use the Upload mode to process images instead.

Camera inactive

Position mathematics clearly in view. Captured photos will be processed using the same options as uploaded files.

Verify Your Upload

Filename:
Pages detected:
File size:

Processing Options Include equation numbering

Adds equation tags like \tag{1.2} to numbered equations

Maths delimiter format LaTeX format Markdown format

Include page headers and numbers

Keeps page numbers, headers, and footers from source images

Ready to process

Original Mathematics

Processed Output

Human-readable

Confidence:

Mathematical Output

Confidence:: -
Type:: -
Available formats:: -

LaTeX Output

MathML Output

AsciiMath Output

HTML Output

Preview:

Markdown Output

JSON Output

Chemistry Output

Chemical Identifiers

Molecular Formula: —
Name: —
Molecular Weight: —
SMILES: —
InChI: —
InChI Key: —

Table (HTML) Output

Preserve inline table styling

Unchecked: removes inline styles for custom CSS styling

Table (Markdown) Output

Table (TSV) Output

Developer Information

Transaction Summary

Endpoint:: Not yet processed
Operation Type:: Not yet processed
Request Timing:: Not yet processed
Confidence:: Not yet processed
Content Type:: Not yet processed

Request Data

No request data available yet

Response Data

No response data available yet

API Metadata

Request ID:: Not yet processed
Processing Model:: Not yet processed
API Version:: v3
Image Dimensions:: Not yet processed
Auto-Rotation:: Not yet processed
Confidence Rate:: Not yet processed

API Configuration

Manage all API credentials in Set Up

MathPix Server Location

United States US East 1 (N. Virginia)

Full feature support. Best for users in Americas. Data processed in US.

European Union EU (Frankfurt / Falkenstein)

GDPR Compliant. Best for EU/UK users. Your documents, results and derivatives stay in the EU. All output formats are available.

Asia Pacific SE Asia (Singapore)

Best for users in Asia Pacific region. Data processed in Singapore.

Image Describer

Generate accessible alt text descriptions for images using AI.

Ally Accessibility Reporting

Select Report Type

Module Report Accessibility Statement Preview Report Builder

API Status:

Not configured

Module Report

Generate a detailed accessibility report for a single module. Search for and select a module to view comprehensive accessibility metrics, content inventory, and issue breakdown.

Find a Module

Select a module above to enable this button

Accessibility Statement Preview

Preview the accessibility statement that students will see for a selected module. This shows a simplified, student-facing summary of potential accessibility barriers.

Institution and environment

Choose your institution and virtual learning environment. This adjusts wording throughout the statement, such as "module lead" or "Blackboard".

Accessibility Statement Settings

Show

Choose which parts of the statement appear — on screen and in every export. The module information is always included.

Boilerplate Lead answers Ally data

Exports

Allow data updates in exports

When enabled, exported statements include an "Update accessibility data" button that refreshes the accessibility-data section against the live Ally data. This is read at export time, so it only affects statements you export from now on. Leave it off to export a fixed snapshot.

Open exports in focus mode

When enabled, statements you export open in focus mode: a distraction-free reading view with the sidebar and table of contents hidden. Readers can leave focus mode at any time with the Escape key or the on-screen toggle. This is read at export time, so it only affects statements you export from now on.

Find a Module

Select a module first to enable this button Select a module first to enable this button

Build Query

Report Type

Overall Scores Module accessibility scores and file type counts

Issues Breakdown Accessibility issues by category and severity

Find a Module

Quick Filters

Term

Department

Active modules only

Advanced Filters

Sort & Pagination

Sort by

Order

Results limit

Developer Information

Transaction Summary

Endpoint:: —
Region:: —
Request Timing:: —
Records Returned:: —
API Status:: —

Request Data

No request data available

Response Data

No response data available

API Configuration & Settings

Server Region

Select the region where your Ally instance is hosted.

Client ID

API Token

Obtain from: Institutional Report → Export → Connect external tool

Proxy Worker URL (alternative to an API token)

A proxy worker holds the Ally token for you, so you can run queries without entering one. You still need a Client ID and region. If you provide both a token and a worker URL, the token is used. This URL is not a secret, so unticking Remember credentials keeps it. Clearing your credentials removes it, and so does emptying this box and selecting Save credentials.

Remember credentials in this browser

Manage all API credentials in Set Up

Chat

Filter models by name or provider

Model No model selected

More filters

Pricing options

Show only free models

Sort by price, cheapest first

Cost range (per 1M tokens)

Prices are US dollars per million tokens. Foundry models are hidden while a price filter or sort is on.

Price range

Model capabilities

Vision/Image processing

Code generation

Advanced reasoning

Tool calling/Function calling

Model provider

Filter by provider

Model information

System prompt

Preset

Parameters

Temperature 0.7

Balanced creativity and consistency

Top-P 1.00

Nucleus sampling. At 1 it has no effect.

Word Variety 0.0

Controls how much the model repeats individual words. Higher values encourage a wider vocabulary; lower values allow more word repetition. Values below 0 encourage repeating words, which can help keep the response consistent.

Phrase Variety 0.0

Controls how much the model repeats phrases and ideas. Higher values encourage new phrasing and fresh topics; lower values allow more repetition. Values below 0 encourage repetition, which can help keep the response consistent.

Maximum response length 1024

Moderate length responses

Attach an image, or drag and drop

JPEG, PNG or WebP up to 10MB, or PDF up to 25MB.

Voice Settings

Developer information

Finish reason

Not reported

Request

Response

Local Chat

Chat with a local AI model running entirely in your browser. No data leaves your device.

Model Not loaded

Model information

System prompt

Preset

Parameters

Temperature 0.7

Balanced creativity and consistency

Max tokens 1024

Moderate length responses

Voice Settings