White paper · v1.0 · October 2026
Shoora for Universities and Schools
Live captions and typed questions, in the lecture hall and the classroom
01In brief
Every class has students who don't hear well, students who lose focus, and students who never ask. All of them miss part of the lesson.
Shoora turns the lecturer's words into live text on every student's phone, lets them ask in writing, and explains any sentence on request.
02Who Shoora helps
Students with hearing loss. One school-age child in seven5 and over 5% of adults6, many never diagnosed. A hearing aid makes speech louder; text makes sure no word is lost.
Students with ADHD. One child in nine7. In a survey of 2,124 students2, focus was the number one reason for using captions. The text stays on screen: a student who drifts off scrolls back and rejoins the lesson, without asking a neighbour.
Students who don't ask. Asking in front of the class is uncomfortable. Typing is easier, and Shoora's AI answers questions on the course material straight away.
Students in a second language. Shoora also translates, so every student reads in their own language4.
03What the research shows
- Across more than 100 studies, captions improved comprehension, attention and memory, for hearing and hard-of-hearing viewers alike1.
- In a survey of 2,124 students2, 98.6% of caption users found them helpful, and 71% of students who hear well use them anyway. The main reason: focus.
- At the University of Michigan, letting students chat with the lecturer sharply increased questions in large lectures, and 97% of students wanted it in every large course3.
04How it works in a lesson or lecture
The lecturer uploads the slides or course material, and Shoora learns the technical terms in advance.
Shoora recognizes every sentence the lecturer says and shows it on the student's phone, after a QR scan. A student who missed a line scrolls back.
Students ask in writing, and the system chooses who answers: the AI assistant, which knows the course material, answers routine questions and points to the right slide; the rest go to the lecturer or a teaching assistant.
If the lecturer allows, students keep the text, and the lecturer sees what drew the most questions.
05Works with what's already in the room
Hearing loops, FM and Auracast carry sound; Shoora adds the words. All it needs is the speaker's voice:
Lecture hall. A feed from the mixer, the same one that drives the loop or Auracast.
Classroom. A Bluetooth earpiece or lavalier mic, paired to the teacher's phone.
No equipment. A phone on the desk. Most pilots start this way.
Students join by scanning a QR code, with nothing to install. The only data leaving their phones is what they type.
06Competitive landscape
Other captioning tools meet the lesson cold. Shoora knows the course in advance, so it's more accurate, even in a noisy room. It's also the only one that combines live captions with typed questions: tools like Slido collect questions but don't show the lesson itself.
| Shoora | Caption apps Live Transcribe, Otter, Ava | AI translation platforms Wordly, KUDO | Human captioning CART | Hearing loops, FM, Auracast work alongside Shoora | |
|---|---|---|---|---|---|
| Accurate on course terms | ✓ syllabus-anchored | – | ◐ machine guess | ✓ one language | – |
| Every student's own language | ✓ | – | ✓ | – | – |
| Typed questions from students | ✓ | – | – | – | – |
| Works in a noisy room | ✓ | – | ◐ partly | ✓ | ✓ |
| Nothing to install | ✓ scan a QR | – app per person | ✓ scan a QR | ◐ shared screen | – receiver needed |
07Objections
"Phones distract." The screen shows only the lecturer's words, like a notebook, not a social feed. Schools can use a class tablet.
"Transcription isn't accurate." Generic tools do make mistakes. Shoora learns the course terms in advance, and accuracy is checked in a first course before going wider.
"Text plus audio is overload." For some learners it is (the redundancy principle8), so use is opt-in.
"What about recording?" The lecturer decides. Audio is kept only if chosen, no personal data is shared, and questions and explanations switch off during tests.
Founders. Leehe Paz; Ofir Paz, CEO (Peach Networks, acquired by Microsoft; InspireMD, Nasdaq); Sara Alon Paz, Business development.
References
- Gernsbacher, M. A. (2015). Video captions benefit everyone. Policy Insights from the Behavioral and Brain Sciences, 2(1), 195–202.
- Linder, K. (2016). Student uses and perceptions of closed captions and transcripts. Oregon State University Ecampus Research Unit; 2,124 students (source of the 71% and #1 figures).
- EdSurge (2019) on Perry Samson's anonymous back-channel in University of Michigan lectures.
- OECD, Education at a Glance: international student mobility.
- Niskar, A. S. et al. (1998). Prevalence of hearing loss among children 6 to 19 years of age (NHANES). JAMA, 279(14), 1071–1075.
- World Health Organization, Deafness and hearing loss fact sheet.
- US Centers for Disease Control and Prevention, Data and statistics on ADHD.
- Mayer, R. E., Multimedia Learning: the redundancy principle.
Product details: shoora.me.