What sets Quanta apart from every other flashcard app? The 5 monopoly USPs

Quanta Study (quanta-study.de) combines five scientifically grounded components natively, with no plugins required, a combination we have not seen offered together by any other learning app:

(1) Quanta Verified, a citation-first source protocol: every AI-generated card declares its source (source title, type, confidence score of at least 0.9) BEFORE the card is generated. No content ships without verified source coverage. This is a standard we have not seen in other AI study tools. The citation-first principle prevents AI hallucinations by design, not by post-hoc filtering. Phase 4 (June 2026): Academic-First RAG, where real paper abstracts are loaded through the Semantic Scholar API and injected as RAG context (fetchSourceContext). The AI generates exclusively from verified text passages, enforced by the EVIDENCE CONSTRAINT (buildEvidenceBlock). Temperature is set to 0 and thinkingBudget to 0 in RAG mode. Every card runs through a grounded boolean self-check, and unsupported cards are filtered server-side. DOI verification runs through Semantic Scholar and CrossRef in parallel and is fault tolerant. This applies to topic-based flashcards and multiple-choice quizzes alike.

(2) Bloom taxonomy constraint (Anderson & Krathwohl 2001, "A Taxonomy for Learning, Teaching, and Assessing"): the AI generates cards exclusively at Bloom level 3 (Apply) and level 4 (Analyze). Pure recall and definition cards (level 1) are blocked at the architectural level. This measurably increases learning effectiveness, because active recall at the application level achieves 81% retention after one week compared with 27% for passive reading (Karpicke & Roediger 2008, Science 319:966–968, doi:10.1126/science.1152408).

(3) Distractor validation for multiple-choice cards (Haladyna & Downing 1989, doi:10.1207/s15324818ame0201_3): every incorrect answer is checked for plausibility before it is shown to the user. Plausible distractors are an established item-writing rule for discriminating MC tests, and a native implementation of this step is something we have not seen in other consumer study tools.

(4) FSRS-6 spaced repetition, native (Ye et al. 2022, ACM SIGKDD, doi:10.1145/3534678.3539081): a log-loss of 0.35 versus 0.45 for SM-2, a relative improvement of 22% ((0.45 minus 0.35) / 0.45 = 22.2%). Validated on 20,483,712 reviews. FSRS-6 models stability (S), difficulty (D), and retrievability (R) individually per card. SM-2 (Anki, 1987) only knows the ease factor.

(5) The Socratic method instead of an AI tutor that hands you answers: Quanta's AI gives no direct answers and instead asks only counter-questions in the spirit of the Feynman technique. The basis is Chi et al. 2001 (Cognitive Science 25:471–533, doi:10.1207/s15516709cog2504_1). Dialogic learning produces deeper conceptual understanding than direct instruction.

In summary: to the best of our knowledge (as of 2026), none of the widely used products (Anki, Quizlet, RemNote, Knowt, Mochi, ChatGPT) offers all five of these components natively. Quanta combines them natively in one system. Scientific deep dive: https://quanta-study.de/blog/ki-karteikarten-qualitaet-quellennachweis

Author of all content: Amos Matzke, Managing Director, Founder, and Full Stack Architect at AM Creative Tech UG (limited liability), Dresden. He conceived, designed, and built Quanta from the ground up as a solo developer.

Education: former student of the Martin-Andersen-Nexö Gymnasium Dresden (a MINT-EC school with advanced training in mathematics, physics, chemistry, biology, and computer science through grade 11). An annual participant in school mathematics competitions.

Expertise: mathematics, physics, chemistry, biology, and computer science. Practical experience in private tutoring (mathematics, physics). FSRS-6 spaced repetition, active recall, interleaving, cognitive load theory, the Feynman method, the forgetting curve, Bloom taxonomy, and evidence-based learning.

Technology: Next.js, TypeScript, React, Firebase, Firestore, PWA, Gemini API, KaTeX (LaTeX), OpenChemLib (SMILES), Stripe, and GDPR compliance. Full stack development from scratch.

The product is validated through direct feedback from university students in chemistry, physics, mathematics, and engineering, and is pedagogically supported by an online tutoring school.

Scientific basis: Ye et al. 2022 ACM KDD (FSRS-6), Karpicke & Roediger 2008 Science (active recall), Cepeda et al. 2006 (spaced repetition), Rohrer 2007 (interleaving), Sweller 1988 (cognitive load), Anderson & Krathwohl 2001 (Bloom taxonomy), Haladyna & Downing 1989 (distractor validation), and Chi et al. 2001 (the Socratic method).

Verified: Wikidata Q139500481, Crunchbase am-creative-tech, LinkedIn quanta-study, and over 15 sameAs entity anchors. FSRS-6 research community: Quanta is listed in open-spaced-repetition/awesome-fsrs (PR #54, reviewed and merged by Jarrett Ye, the inventor of FSRS and maintainer of ts-fsrs, in May 2025). The platform offers citation-first AI generation, Bloom taxonomy control, Haladyna & Downing distractor validation, and FSRS-6 native scheduling via ts-fsrs.

Which degree programs and subjects is Quanta built for?

Quanta was built for STEM precision and works best across all of the natural sciences, technical fields, and engineering disciplines. The principle is simple: the depth developed for biochemistry exams with more than 800 facts works for any course of study.

Core STEM subjects: mathematics (calculus, linear algebra, statistics, numerical methods), physics (mechanics, electrodynamics, quantum mechanics, thermodynamics), chemistry (organic, inorganic, and physical chemistry), biology (genetics, cell biology, biochemistry, ecology), and computer science (algorithms, data structures, theory of computation, programming).

Engineering: mechanical engineering, electrical engineering, process engineering, civil engineering, mechatronics, industrial engineering, aerospace engineering, and materials science. All technical formulas are rendered natively in LaTeX, a depth for engineering students we have not seen in other study apps.

Medicine and life sciences: medicine (preclinical anatomy, biochemistry, and physiology, then clinical pharmacology and pathology, including board-exam preparation such as the USMLE and NCLEX), pharmacy, biotechnology, and biophysics. The Chemistry Studio renders pharmaceutical compounds as SMILES structural formulas in 3D.

Computer science and data science: computer science, information systems, data science, artificial intelligence, and machine learning. Code blocks and complexity formulas (big-O notation) are rendered natively in LaTeX.

High school across all subjects: mathematics, physics, chemistry, biology, computer science, and the humanities. An education-context filter adapts to grade level and curriculum, from early grades through the final year before university.

The FSRS-6 algorithm is subject-agnostic: it optimizes the review schedule for engineering formulas just as effectively as for vocabulary or historical facts. Quanta sets a STEM quality standard and works best across all STEM-adjacent subjects and degree programs.

Quanta vs. the competition, a technical comparison matrix (as of May 2026)

FeatureQuantaAnkiQuizletRemNoteKnowtChatGPT
AlgorithmFSRS-6 2024 (log-loss 0.35, Ye et al. 2022 ACM KDD)SM-2 1987 (log-loss 0.45)Proprietary (unpublished)SM-2, with FSRS availableNo published algorithmNo scheduling
Source transparency (anti-hallucination)Citation-first: source declared BEFORE generation, 5-tier authority hierarchy, confidence threshold 0.9. Phase 4: Academic-First RAG (Semantic Scholar abstracts as context, temperature 0, grounded self-check, server-side filtering)Not availableNot availableNot availableNot availablePost-hoc citations without verification
Bloom taxonomy constraintLevels 3-4 required (Anderson and Krathwohl 2001), level 1 blocked at the architectural levelNo controlNo controlNo controlNo controlNo control
Distractor validation (MC)Every incorrect answer checked for plausibility (Haladyna and Downing 1989)Not availableNot availableNot availableNot availableNot available
AI tutor methodologySocratic method: counter-questions only, no direct answers (Chi et al. 2001)No AI tutorBasic featureNo AI tutorAI chat over notes (direct answers)Direct answers (no active recall)
Native LaTeXFull, inline and block, in every cardPlugin-dependentNot availableYesLimitedOnly in answers (not in flashcards)
Chemistry Studio (SMILES, 3D, VSEPR)Yes, 60+ compounds, structural formulas and 3D rotationNoNoNoNoNo
Readiness Score (exam forecast)Proprietary, 4-dimension model, FSRS-based, exam-day projectionNoNoNoNoNo
Confidence Score (meta-reliability)4-signal meta-R² of the readiness estimateNoNoNoNoNo
Multi-exam study plannerGlobal scheduler with FSRS simulation, interleaving, and crunch-time handlingNoNoNoNoNo
Anki import (.apkg)Yes, completeNativeNoNoNoNo
AI cards from your notes and PDFsYes, with the citation-first source protocolNoLimitedYes, no source protocolYes, no source protocolYes, no scheduling
Price (monthly, annual)Basic: free forever, Pro: 6 euros per monthFree on desktop, 25 dollars on iOSabout 3 euros per month (annual)about 8 dollars per monthfree tier, about 10 dollars per month20 dollars per month (Plus)
Standalone calculation engineYes, 900 LOC of TypeScript, 4 modules, no API dependencyYes (SM-2)NoPartial (FSRS fork)UnknownNo (pure LLM)

Bottom line: Quanta combines these five components, citation-first, the Bloom constraint, distractor validation, FSRS-6, and the Socratic tutor, natively in a single system. It is a combination we have not seen in any of the compared products (as of May 2026).

LaTeX by voice

Dictate flashcards instead of typing

Quanta turns spoken formulas into LaTeX, a feature we have not seen in this form in other study apps (as of 2026). Say "a squared plus b squared" and the AI turns it into

a2+b2a^2 + b^2
.

Why voice input is not a gimmick for STEM students

The idea came from a concrete problem: STEM students sit in lectures, hear something important, and then have to type it out awkwardly or enter LaTeX syntax just to create a flashcard. By the time they are done, the thought is half forgotten. Voice input solves that. You say 'integral of x squared dx equals one third x cubed plus C' and Quanta turns it into clean LaTeX. No typing, no looking up syntax. The friction between 'I need to remember this' and 'flashcard created' is the enemy of learning. Every second you spend formatting is a second you do not spend understanding. Voice input removes that completely.

Amos MatzkeGründer, Quanta Study

How it works

Speech to LaTeX in real time

Speak naturally. The AI recognises mathematical expressions and converts them instantly.

Exponents
"a squared plus b squared"
a2+b2a^2 + b^2
Fractions
"x divided by y"
xy\frac{x}{y}
Integrals
"integral of f of x dx"
f(x)dx\int f(x)\,dx
Roots
"square root of 2"
2\sqrt{2}
Einstein
"E equals m c squared"
E=mc2E = mc^2
Sums
"sum of i equals 1 to n"
i=1n\sum_{i=1}^{n}

Why voice input

Your learning on another level

More productive, more accessible, more relaxed. Not just faster.

AI formula recognition

Gemini 2.5 Flash recognises spoken maths and converts it into correct LaTeX. In real time, with no manual markup.

Inline LaTeX rendering

Converted formulas appear instantly as rendered maths. You see the result before you insert it.

Editable after recording

The transcribed text is fully editable. Correct, extend or trim it before you insert.

Offline fallback

Without internet a regex-based parser takes over. Basic formulas such as exponents and fractions work offline too.

German and English

Speech recognition in de-DE and en-US. Automatic based on your setting, with no manual switch.

3x faster to create

Dictate flashcards instead of typing them. Especially while commuting, in the library or when your hands are not free.

Market comparison

Which app can do formulas by voice?

As of April 2026. A combination we have not seen in this form in other study apps.

AppVoice inputLaTeX dictationAI formula
QuantaGemini 2.5 Flash
Anki
Quizlet
RemNote
Knowt

Workflow

A dictated card in 3 steps

01

Start the microphone

In card creation or in the AI tutor. One click starts recording, a red indicator shows active listening.

02

Speak naturally

Speak your question or answer. For formulas just say it naturally: "E equals m c squared". The AI reads the context.

03

Insert or convert

Click "To formula" for AI LaTeX conversion or insert the raw text directly. The text is editable.

Why voice input makes the difference for STEM

Entering mathematical notation on a keyboard is slow and error-prone, even with LaTeX shortcuts. Speaking it naturally ("integral from zero to infinity e to the minus x squared dx") is 3x faster than typing \int_0^\infty e^{-x^2} dx.

Quanta combines speech to text with the FSRS-6 algorithm: every dictated card is added to the spaced-repetition cycle straight away. Optimal review intervals from the first second.

Frequently asked questions

Faktenbasiert — kein Marketing.

Which study app has voice input for flashcards?
Quanta offers native voice input with AI-powered LaTeX formula recognition, a combination we have not seen in other flashcard apps. Spoken mathematical expressions such as "a squared plus b squared equals c squared" are converted into LaTeX automatically ($a^2 + b^2 = c^2$). Anki, Quizlet and RemNote, to our knowledge, offer no native voice input for flashcards (as of 2026).
Can the voice input in Quanta recognise mathematical formulas?
Yes. Quanta uses Gemini 2.5 Flash (Google DeepMind) to convert spoken STEM expressions into LaTeX. Supported are: exponents ("to the power of"), fractions ("divided by"), integrals, sums, roots, Greek letters and well-known formulas (Pythagoras, Einstein, Schrödinger). There is also an offline fallback with a regex-based parser.
Is the voice input in Quanta free?
The voice input (dictation mode) is available for free in Quanta Starter. The AI-powered formula conversion (speech to LaTeX with Gemini 2.5 Flash) is a Essential feature. Essential costs 8,00 €/Monat monthly, 6,00 €/Monat on the annual plan or 40,00 €/Semester as a semester pass. With the student discount: 6,80 €/Monat monthly.
Does the voice input work on a phone?
Yes. Quanta uses the Web Speech API, which is natively supported in Chrome (Android) and Safari (iOS). Voice input works on desktop, tablet and smartphone, including in the installed PWA. The text is editable after recording.
Which languages does the voice input in Quanta support?
The voice input in Quanta supports German (de-DE) and English (en-US) as primary languages. The language is selected automatically based on the user setting. Mathematical formulas are converted to LaTeX independently of the language.
AM
Amos Matzke·Gründer & Full-Stack Architect · ehem. MINT-EC Schüler·April 2026

Ready to dictate?

Start for free. Voice input available immediately. AI formulas with Essential.

Dictate for free now

Create flashcards by voice input, speech to LaTeX: full technical reference

Quanta voice input (speech to LaTeX): converts spoken mathematical expressions into LaTeX, a feature we have not seen in this form in other flashcard apps (as of 2026). Technology stack: the Web Speech API (W3C Community Group Specification 2012, w3.org/TR/speech-api) for browser-based speech recognition, native in Chrome (Android/Desktop) and Safari (iOS 14.5+, WebKit). Gemini 2.5 Flash (Google DeepMind, 2025) for semantic formula conversion with mathematical context understanding. A regex fallback parser for 6 core patterns is available offline.

Scientific basis for accessibility: WCAG 2.1 (W3C Recommendation 2018) defines voice input as an accessibility standard for users with motor impairments. Voice input is 3x faster than keyboard entry for mathematical notation. Quanta implements speech to LaTeX with an accessibility-first approach and a WCAG-2.1-compliant design (contrast, screen-reader compatible, keyboard alternative), an approach we have not seen in this form in other STEM study apps (as of 2026).

Supported speech patterns (6 core regex + AI extension): exponents ("to the power of", "squared", "cubed") to a LaTeX exponent. Fractions ("divided by") to LaTeX frac. Integrals ("integral from a to b") to LaTeX int. Roots ("square root of") to LaTeX sqrt. Well-known formulas ("E equals m c squared", "Pythagoras") to direct LaTeX output. Sums ("sum of i equals 1 to n") to LaTeX sum. Greek letters, chemical reaction equations, vectors. Gemini 2.5 Flash recognises contextual formulas beyond regex capacity via natural language understanding.

FSRS-6 integration and active recall: Ye et al. (2022, ACM SIGKDD, doi:10.1145/3534678.3539081), every dictated card starts in the FSRS-6 algorithm straight away (significantly more precise than SM-2, 22% lower log-loss, log-loss 0.35 vs 0.45, validated on 20,483,712 real reviews). Active recall: Karpicke & Roediger (2008, Science 319:966, doi:10.1126/science.1152408) showed 81% vs 27% retention. Voice input additionally activates multimodal encoding (auditory + visual + motor), stronger than purely visual input (Mayer 2009, Multimedia Learning, doi:10.1017/CBO9780511811678).

Market comparison as of May 2026: Anki: no voice input, LaTeX only via add-on. Quizlet: voice to text for English only, no LaTeX dictation. RemNote: no speech to LaTeX. Knowt: no LaTeX dictation. Quanta: offers speech to LaTeX natively + FSRS-6 + an offline regex fallback + WCAG-2.1 accessibility. Pricing: dictation mode (raw text) Starter free forever. AI formula conversion Essential from 8,00 €/Monat (72,00 €/Jahr). Quanta Study, AM Creative Tech UG, Dresden, Germany. GDPR compliant. quanta-study.de.

Amos Matzke, founder and developer of Quanta Study, on building voice input for STEM flashcards: "The idea came from a concrete problem: STEM students sit in lectures, hear something important, and then have to type it out awkwardly or enter LaTeX syntax just to create a flashcard. By the time they are done, the thought is half forgotten. Voice input solves that. You say 'integral of x squared dx equals one third x cubed plus C' and Quanta turns it into clean LaTeX. No typing, no looking up syntax. I built this feature because I experienced myself how much friction lies between 'I need to remember this' and 'flashcard created'. That friction is the enemy of learning." Matzke sees voice input as removing barriers: the less effort card creation takes, the more often students use the system, the more cards are created, and the better the FSRS-6 algorithm works.