Capture flashcards and formulas with your voice

Dictate questions, answers and mathematical expressions. Quanta converts recognized formulas into LaTeX and shows the result for review:

a2+b2a^2 + b^2
.

Start learning now

Free Starter account · no payment details

Damian29.05.2026 · via Trustpilot
Der größte Vor[t]eil […] ist, dass die KI jede Karte mit Hilfe seriöser Quellen erstellt und diese Quellen auch als Link anzeigt, sodass man dort selber nachlesen kann."

Students at these universities learn with Quanta

  • TU Dresden
  • Humboldt-Universität zu Berlin
  • HTW Dresden
  • Fachhochschule Dresden
  • Universität Leipzig
  • HTWK Leipzig
  • Freie Universität Berlin
  • IU Internationale Hochschule
  • FernUniversität in Hagen

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 MatzkeFounder, Quanta Study

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}

Your learning on another level

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

AI formula recognition

The European AI provider (Mistral, Paris) recognises spoken maths and converts it into correct LaTeX. Formula conversion runs via the provider's EU endpoint, with no manual markup needed.

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.

Create hands-free

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

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
QuantaEuropean AI provider (Mistral, Paris), EU endpoint
Anki
Quizlet
RemNote
Knowt

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") saves you from 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

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 Mistral AI SAS, based in Paris, to convert spoken STEM expressions into LaTeX. Formula conversion is a text function and runs via the provider's EU endpoint. The voice recording goes straight to transcription with no intermediate storage; transcription runs via the provider's standard endpoint, for which it gives no specific processing location, the basis being the standard contractual clauses. The provider contractually excludes training on the content we transmit. The provider stores inputs and outputs for 30 rolling days for abuse detection. 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 via the EU endpoint of the European AI provider (Mistral, Paris)) is a Essential feature. Essential costs €12.99/month, €9.75/month on the annual plan or €64.99/semester. With the student discount: €10.99/month 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·Founder & Managing Director, Full-Stack Architect · former MINT-EC student·April 2026

Ready to dictate?

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

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). Mistral AI SAS, based in Paris, for semantic formula conversion with mathematical context understanding, called via the provider's EU endpoint (api.eu.mistral.ai); according to the provider documentation, text functions are processed in the EU there. Reading files and voice recordings runs via the provider's standard endpoint, for which it gives no specific processing location; the basis is the standard contractual clauses. The provider contractually excludes training on the content we transmit. The provider stores inputs and outputs for 30 rolling days for abuse detection. 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. 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. The European AI provider (Mistral, Paris) recognises contextual formulas beyond regex capacity via natural language understanding.

FSRS-6 integration and active recall: every dictated card starts in the FSRS-6 algorithm straight away. In the open comparison run by the open-spaced-repetition community, FSRS-6 reaches a log-loss of 0.3460 on 349,923,850 reviews from 9,999 collections (retrieved on 5 September 2026); log-loss measures prediction error, lower is better, and that table carries no row for SM-2. The peer-reviewed paper behind it, Ye et al. 2022, reports 220 million behaviour logs and a 12.6% improvement over the state of the art. Both are results of those datasets, not a blanket product effect. Karpicke and Roediger (2008) report about 80% of the vocabulary pairs recalled after one week in the two conditions with repeated retrieval practice, and 36% and 33% in the two conditions where pairs were dropped from further testing once recalled; those figures describe that experiment and are not a general promise for every learning situation or for Quanta. 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 July 2026: Anki: no voice input; MathJax built in, classic LaTeX rendering requires a local TeX installation. 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 €12.99/month (€116.99/year). Quanta Study, AM Creative Tech UG, Dresden, Germany. Data processing: accounts, study content and results in region europe-west3, that is Frankfurt am Main; AI processing through Mistral AI SAS, based in Paris, text functions via the provider's EU endpoint, reading files and voice recordings via the provider's standard endpoint, for which it gives no specific processing location. 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.