Select Words in motion and start the camera. Automatic words watches for movement; sign once, then pause briefly.
Camera offExpression: Camera offVisible facial movements · not a measure of emotion
Camera diagnostics
Local status only; no images or hand coordinates. Copy this report when a sign fails.
Start the camera to collect diagnostics.
Use a well-lit space and keep your palm facing the camera.
Words in motion · Experimental
Daily conversation · five-word preview
NAME · HOME · HAVE · WANT · LOVE
Experimental: 44/66 held-out word clips matched; 2/48 unsupported signs were falsely accepted. This preview has limited accuracy. Review every suggestion. Results are not live-camera accuracy.
Video stays on your device. Recorded coordinates are processed in memory and not stored. With Automatic words enabled, sign once and pause to send a captured sequence automatically. Review each match before adding it; optional automatic adding uses the setting below. Recording manually is still available.
Loading five-word preview…
Enabled by default: DRINK, WATER, BOOK, FOOD, HUNGRY, LIKE, GO. New words often miss; GO did not match in our small test. This preview can add false suggestions. Recognition checks
Loading the seven extra words…
Loading pretrained words…
Loading pretrained vocabulary…
Pretrained vocabulary will appear here.
Each recording has a 1.5-second countdown, then captures 2.5 seconds of movement. Slow cameras get up to 2 extra seconds to collect 12 frames.
Sign one word, then pause. Add the match to your draft, or turn on automatic adding below. Review the draft before speaking.
Automatic adding can include incorrect words. It never speaks the draft automatically.
Typed words:
Try “I AM HUNGRY.” or “I WANT WATER, PLEASE.” Typed words are not camera detections. This builds reviewed text from separate signs; it does not translate continuous ASL or its grammar. Use Edit message for corrections.
Review before saving or speaking. Saved text is stored on this server; camera frames stay on your device.
✓
Hold each sign steadyLetters are added after a stable detection.
↻
Move between signsLower your hand briefly before repeating a letter.
Your history is private to this browser or your signed-in account.
Connecting to saved messages…
No saved sessions yet.
0Saved sessions
0Detections
0%Average agreement · not probability
0 msAverage letter hold time
Measured recognition results
Five-word server preview · DTW · evaluated 2 October 2026. Isolated ASL Citizen clips with separate training, validation, and test signers. Tracking failures count as misses.
Frozen five-word model: held-out clip results
Word
Correct
Missed
Wrong word
NAME
6 / 11
5
0
HOME
6 / 11
5
0
HAVE
8 / 11
3
0
WANT
15 / 22
7
0
LOVE
9 / 11
2
0
44 / 66 correct; 22 misses. Unsupported signs: 2 false matches in 48 clips. The model did not pass the original zero-false-match release criterion and remains an optional preview.
These results do not measure live webcam accuracy, automatic movement boundaries, or ordinary hand movements. No calibrated confidence percentage is available.
Model identity and other evaluations
Model SHA-256: acd51663999fcbc7c633af22583e788f522a42a151b5fe63a1d3dfac460317ec
These are user ratings, not measured model accuracy. Letter tests · Motion tests. Submit the study’s 5-point evaluation for accuracy, usability, and performance. No account identity is attached to feedback. Administrators can read your comments; avoid personal information.
0 responsesAccuracy —Usability —Performance —
Quick reference
Learn supported signs
Seven static letters are pretrained. Teach the 5 gesture in AI Studio to add it.
Supported & Tested
7 static letters
A · B · I · L · V · W · Y
Pretrained and evaluated on held-out images with detected hands. This is not a live-camera or signer-independent accuracy guarantee.
Default: HELLO, THANK YOU, PLEASE, YES, NO, FINISH.
Also enabled by default: DRINK, WATER, BOOK, FOOD, HUNGRY, LIKE, GO. Server preview: NAME, HOME, HAVE, WANT, LOVE (no sign-in required). These models can miss correct signs or suggest the wrong word. Review every match.
Select Words in motion and start the camera. Automatic words detects movement and suggests a word after you pause. Review the result at the camera. You can also use Record a word for a timed capture. Personal training is optional.
Daily conversation · experimental motion words
Practice NAME, HOME, HAVE, WANT, and LOVE. Use the five-word server preview without signing in or recording training examples. It sends hand landmarks, not video, to the server. You can also teach personal examples for on-device practice. Personal matches are experimental and may be wrong.
Experimental server preview
NAME
Personal training is optional for the server preview.
Watch a lesson, then choose Use five-word preview. Personal training remains optional.
Watch & practice
See the movement.
Choose a word, watch the full movement, then try it at the camera. Local examples are silent. NAME, WANT, and LOVE use embedded ASL University videos; use the player’s playback controls. Follow the instructions for your selected word: automatic capture works for standard words and the enabled five-word server preview.
HELLO · Automatic capture: start the camera, sign once, then pause. Review the match.
Watch the hand shape, direction, and position near the face or body. Keep your hands and upper body visible when practicing. Examples show one signing variant; recognition may still miss a correct sign.
Find a sign by topic, watch an available example, or open a lesson. Recognition badges show which words have an enabled preview model. New category models did not pass evaluation. Other words can be practiced with personal recordings.
Category models load only when selected.
Loading vocabulary…
Emergency and safety entries are learning vocabulary. Recognition can miss or confuse signs, and this website does not contact emergency services.
External lessons open their publisher’s website. ASL signs and phrase grammar vary by context; English phrases are not automatically a single sign. Typed text buttons do not count as camera recognition.
Use only the listed words. Other signs can be mistaken for a supported word. This small PopSign ASL model has limited accuracy; review each suggestion before adding or speaking it. Personal examples stay in this browser. Evaluation results · Dataset credit
Personalized machine learning
Recognize letters, then personalize your signing.
Seven letters come pretrained from ASL image examples. Start the camera to try them, or capture your own examples to personalize recognition. Teach the 5 gesture before using it. Uncertain poses are left blank instead of guessed. Camera frames stay on your device.
21 landmarksOn-device trainingNo images stored
AI training setLoading pretrained letters…
Start the camera above, hold the selected gesture, then capture samples.
Optional: add your own word examples
Record at least three examples for a new word. Removing personal examples keeps the pretrained vocabulary.
LLM sentence interpretation
Turn your reviewed words into a suggested English sentence. Clicking Interpret sends this draft text to a local model on our server. No camera frames are sent and interpretation drafts are not saved automatically.
When enabled, a recognized FINISH sends your accumulated draft to the server LLM and speaks its suggestion. FINISH is not added to the draft. Add each word first, or enable automatic adding above. FINISH uses the default motion model: choose FINISH → Prepare practice after using the five-word server preview. Recognition and interpretation can be wrong. Empty, changed, or unclear drafts are not spoken.
Checking the local model…
Original words
Suggested sentence
The LLM may change the meaning or guess incorrectly. It cannot verify your signs or translate ASL grammar. Suggestions are never applied automatically. Speech is automatic only when you enable the FINISH setting.
Built for inclusion
Communication should feel effortless.
HandSpeak Web is a capstone prototype that uses computer vision to help bridge everyday communication between deaf, hard-of-hearing, and hearing individuals. It recognizes selected static letters and offers an experimental pretrained vocabulary for moving signs. Face landmarks are displayed for visual feedback; they are not used to interpret identity, emotions, or ASL grammar.
7Tested static letters
On-deviceCamera recognition
0frames stored
Help, privacy, and recognition limits
Letters: hold a supported letter steady. Words: select Words in motion, sign once, and pause. Watch the examples first; use Record a word if automatic capture misses the movement.
Camera frames and personal gesture examples stay on your device. The optional five-word preview sends recorded hand-landmark coordinates to the server for in-memory recognition; it does not upload video or save those coordinates. Saving sends your message and letter-detection statistics to this server. Interpret draft sends only the reviewed text to a local model on this server; it does not upload camera footage or save the draft automatically. Your history is linked to your account, or to a cookie when using the site as a guest. You can export or delete your saved messages. Account passwords are hashed; never send your password to the administrator.
Feedback is collected without linking it to your account; administrators can read submitted comments. Email verification and email delivery are not configured. For password recovery, ask the administrator for a private, single-use reset link.
This is an experimental ASL learning and recognition application, not a complete language translator. Similar and unsupported signs can be misidentified. Extra-word recognition is a preview. Always review suggestions before adding or speaking them.