Upload Speech Recording
Click or drag & drop your audio/video file here
Supported Formats
Video: MP4, WebM, MOV, AVI, MKV
Audio: MP3, WAV, M4A
Files over 50 MB will be automatically compressed. Very large files may take longer to process.
Match Videos to Students
Select the student for each video. All videos will be processed with the same rubric and assignment type.
| Video File | Size | Student * | Status | Actions |
|---|
Processing Videos
| Video | Student | Status |
|---|
Processing Complete
| Video File | Student | Status | Actions |
|---|
Evaluating Speech
Loading analytics…
Appearance
Customize the look and feel of the application
Switch between light and dark themes
Account Settings
Manage your account and password
Change Password
Update your password to keep your account secure.
Reset Password via Email
If you've forgotten your password, we can send you a reset link via email.
Report an Error
Encountered a problem? Report it to help us improve the application.
Consent Management
Generate unique consent links for students and manage data use consent
Generate unique consent links for students. Email each student their link; when they open it and submit, their response is saved in the database.
| Student | Status | Consent link | Actions |
|---|
Error Reports
View the status of errors you've reported and report new issues
Report an Error
Encountered a problem? Report it to help us improve the application.
Your Reported Errors
Here you can see all the errors you've reported and track their status. When an administrator updates the status or resolves an issue, you'll see it here.
Loading your error reports...
SpeechGradebook v1.0
New to SpeechGradebook? Follow these steps to run your first evaluation in minutes.
Step 1: Set up a course and rubric
- Go to Dashboard → Courses and select New Course.
- Enter the course name, term, year, and modality, then save.
- Add students to the course using the roster tool.
- Go to Dashboard → Rubrics. Select an existing rubric or create a new one.
Tip: You can import a rubric from a PDF, image, Google Sheet, or Excel file using Import Rubric from File.
Step 2: Run an evaluation
- Select Evaluate Speech in the navigation bar.
- Upload the student's recording. Supported formats: MP3, MP4, MOV, WAV, M4A, WebM. Files over 50 MB are compressed automatically.
- Select a course, student, and rubric.
- Select Continue to Evaluation. The SpeechGradebook Model analyzes the recording against your rubric criteria.
- Review the results. You can download a PDF report or email the student directly from the results screen.
Evaluations are processed by the SpeechGradebook Model, a fine-tuned version of Qwen running on Modal. No external API key is required.
Step 3: Collect student consent
Before storing evaluations in the cloud, students must give consent. Go to Settings → Consent to generate a consent link for your course. Share the link with students — they complete a short form, and their status updates automatically. Evaluations for students who haven't consented remain local only.
Step 4: Review course insights
After running several evaluations, go to Dashboard → Course Insights to see score trends, category breakdowns, and comparisons across students. Use the Export tab to download data. Admin Super Admin users see department- and institution-wide views with instructor filters.
Admin and institution management Admin Super Admin
Admins can view and filter all courses in Settings → Admin. Super Admins can create and configure institutions and manage global settings.
A complete reference for every feature in SpeechGradebook, organized by task area.
Navigation
The navigation bar provides access to all major areas of the app. What you see depends on your account role.
- Evaluate Speech — Upload a recording and run an evaluation.
- Dashboard — Manage courses, rubrics, and analytics. Includes Courses, Rubrics, and Course Insights tabs. Visibility of tabs depends on your role.
- Settings — Configure consent settings and (for admins) institution settings.
- Support — This documentation area.
Running an evaluation
The evaluation flow is a step-by-step wizard:
- Upload — Select an audio or video file. Videos over 50 MB are compressed automatically before submission.
- Course, student, and rubric — Select existing entries or create new ones inline.
- Evaluate — Select Continue to Evaluation. The SpeechGradebook Model analyzes the recording against your rubric criteria.
- Results — Review scores and AI feedback by category. Download a PDF report or email results to the student.
Supported formats: MP3, MP4, MOV/QuickTime, WAV, M4A, WebM.
Editing an evaluation
You can edit any saved evaluation to adjust scores, grades, or comments.
- Go to a student's evaluations and open the evaluation you want to change.
- Select Edit from the evaluation menu (•••).
- The evaluation opens in editing mode. The video or audio player stays visible as you scroll so you can review the recording while making changes.
- For each criterion, select a letter grade (A–F) or enter a point value directly. Grades and points stay in sync automatically.
- Add per-criterion comments in the Comments field below each row, and section-level notes in the Section Notes area.
- Add timeline markers by double-clicking the video at a moment you want to annotate.
- Select Save when finished. Changes are saved to the cloud.
Courses Instructor
Courses organize your students and their evaluations in one place.
- Create a course — Go to Dashboard → Courses and select New Course. Enter a name, term, year, and modality.
- Add students — Open the course and use the roster to add students individually or in bulk.
- View evaluations — Select a student to see their full evaluation history, scores, and trends.
- Customize — Use the course card menu (•••) to rename, customize the card color, or delete the course.
Rubrics Instructor
Rubrics define the criteria and point values the model uses to evaluate a speech. You can create rubrics manually or import them from an existing file.
- Create manually — Go to Dashboard → Rubrics → New Rubric. Add categories, subcategories, and point values.
- Import from file — Use Import Rubric from File to extract criteria from a PDF, image (PNG/JPG), Google Sheet, or Excel file. SpeechGradebook reads the structure and pre-fills the rubric editor.
- Duplicate or edit — Use the rubric card menu to duplicate an existing rubric as a starting point, or edit it directly.
Course Insights Instructor
Course Insights gives you analytics across all evaluations in a course.
- Overview — Summary metrics: average score, score distribution, and evaluation count.
- Comparisons — Score breakdowns by category and comparisons across students or speech types.
- Evaluation list — Searchable, filterable list of all evaluations in the course.
- Export — Download evaluation data as a CSV or formatted report.
Admin and Super Admin users see department- or institution-wide views with instructor filters.
Settings
Settings is divided into tabs based on your role.
- General — Configure the SpeechGradebook Model service URL.
- Consent — Generate per-course consent links to share with students. View each student's consent status.
- Admin Admin — View all courses with instructor and date filters, and access data management tools.
- Admin Super Admin — All admin features plus institution management.
Data management, security, model training, version history, and legal information.
Data management and security
SpeechGradebook uses Supabase for authentication and cloud storage. All data is stored per institution with row-level security (RLS) — each user can only access data their role permits.
- Instructors — Access their own courses, students, rubrics, and evaluations only.
- Admins — Access all data within their department or institution; can filter by instructor and view cross-course analytics.
- Super Admins — Manage institutions and (where configured) cross-institution data.
Student consent — Evaluations for students who haven't given consent are not stored in the cloud. Consent status is tracked in the consent_forms table.
Audit logging — All access to student evaluation data is recorded in audit_logs for FERPA compliance. Each log entry includes the purpose, user, IP address, and user agent.
Model training Super Admin
The SpeechGradebook Model is a fine-tuned version of Qwen trained on your institution's evaluation data. Training runs on Modal (serverless GPU infrastructure), which handles compute provisioning automatically — no server management required.
A trained model gives you scoring behavior calibrated to your rubrics and grading style, with all data remaining within your institution's environment.
To export training data: Go to Settings → Admin → Data Management.
Training guides
- Training Quickstart — Prerequisites, Modal setup, and step-by-step training procedure
- Training README — Quick reference for export, convert, train, and serve commands
- Implementation Guide — Advanced technical documentation for custom deployments
Version history
Recent changes to SpeechGradebook. See CHANGELOG.md in the project repository for the full history.
Licensing and legal
SpeechGradebook is provided for educational use. By using the app, you agree to your institution's terms and any applicable privacy policies. Student data is processed in accordance with FERPA and your institution's data agreements.
Model licensing — The SpeechGradebook Model is a fine-tuned version of Qwen (Apache 2.0 license). If you distribute the model, adapter weights, or any training or serving code that includes the model, you must include the Apache 2.0 license and required attribution. Internal use without redistribution doesn't require including the license in the app. See llm_training/LICENSE for the full license text and third-party notices.
For licensing or legal questions, contact your institution or the support address below.
Contact Support
For questions or technical support, contact: [email protected]