(comments)

原始链接: https://news.ycombinator.com/item?id=43990868

DonEsquire launched YapCards, an iOS app focusing on hands-free, voice-driven flashcard studying for efficient learning on-the-go. It functions like Anki but relies solely on spoken prompts and responses. The app reads a question aloud, and users respond verbally. YapCards then uses AI to evaluate the answer and provide feedback. Key features include voice-only interaction, AI-powered assessment, pre-made lists, and the ability to upload custom Excel lists. It utilizes the SM2 algorithm for spaced repetition. The tech stack includes Swift, Firebase, Deepgram, ElevenLabs, and OpenAI. The creator seeks feedback on voice recognition, latency reduction, and AI accuracy. A suggestion was made to create a demo video. One user questioned the choice of a native app over a website for broader accessibility. Another user expressed concerns about the fallibility of AI in language learning and recommended AI-free audio resources. The creator clarified that prompts and responses are pre-defined, and GPT evaluates semantic meaning.

DonEsquire launched YapCards, an iOS app focusing on hands-free, voice-driven flashcard studying for efficient learning on-the-go. It functions like Anki but relies solely on spoken prompts and responses. The app reads a question aloud, and users respond verbally. YapCards then uses AI to evaluate the answer and provide feedback. Key features include voice-only interaction, AI-powered assessment, pre-made lists, and the ability to upload custom Excel lists. It utilizes the SM2 algorithm for spaced repetition. The tech stack includes Swift, Firebase, Deepgram, ElevenLabs, and OpenAI. The creator seeks feedback on voice recognition, latency reduction, and AI accuracy. A suggestion was made to create a demo video. One user questioned the choice of a native app over a website for broader accessibility. Another user expressed concerns about the fallibility of AI in language learning and recommended AI-free audio resources. The creator clarified that prompts and responses are pre-defined, and GPT evaluates semantic meaning.
相关文章
  • (评论) 2025-04-06
  • (评论) 2025-04-13
  • (评论) 2023-11-20
  • (评论) 2024-05-10
  • 2024-01-28

  • 原文
    Hacker News new | past | comments | ask | show | jobs | submit login
    Show HN: YapCards (iOS) – Voice-driven flashcards with AI feedback
    20 points by DonEsquire 1 day ago | hide | past | favorite | 6 comments
    Testflight Link: https://testflight.apple.com/join/8YzpXxjz

    I wanted to be able to practice Spanish vocab while on my commute to work so I created YapCards. It's an iOS app focused on making flashcard studying hands-free & efficient. Like Anki, but entirely spoken.

    You choose a list to practice, the app reads the prompt out loud (e.g. "What charge does a proton have?"), & you respond by voice. YapCards uses AI to evaluate your response & provide feedback.

    Some key features: Voice-only practice (no need to look at your screen)

    AI evaluation & feedback

    Practice publicly available lists or upload your own excel lists. Publish your lists for others to use

    Uses the SM2 algorithm to manage repetition scheduling

    Tech stack includes Swift, Firebase, Deepgram, ElevenLabs, and OpenAI (trying various models)

    I’d love feedback from fellow learners, developers, or anyone interested in voice interfaces. Especially if you’ve built language tools before — I’m curious about what would make this more useful or sticky. Thoughts around voice recognition / silence detection, reducing latency, and improving AI feedback greatly appreciated!

    Thanks for taking a look.











    should have a demo video


    Hoping to get around to that soon


    What made you choose a native app instead of something more accessible like a website?


    My use case was to have my phone quiz me while I'm driving to work, so simplicity / reduced friction to use when on the go. 1 tap to open the app, 1 tap to select the content (list I want to practice), & 1 tap to start the session.

    Surely a website would open this up to way more ppl. Honestly never even thought of that...



    The first thing I think and my friends think when trying to learn from AI is that it is fallible. ie it makes mistakes and the student has no way of knowing its wrong. GPT 3.5 made grammar mistakes when explaining simple Japanese sentences to me in English. even the CEO of Duolingo said that AI will have "small hits to quality" https://www.linkedin.com/posts/duolingo_below-is-an-all-hand... and my housemate said that the japanese he gets from ChatGPT 4o is awkward. (I told him to prompt it in Japanese instead of English and he said the result was a lot better)

    If trying to learn a language with only audio I recommend an AI-free audio podcast https://coffeebreaklanguages.com/coffeebreakspanish/



    Great points (and appreciate the coffeebreak recommendation!). Totally agree that the AI evaluation has plenty of inconsistency and errors.

    I do want to clarify - it is more like audio only practice for digital flashcards. Meaning the prompt & response are both expected to be defined ahead of time. That way, GPT (as of today), is instructed to evaluate the semantic meaning of the user's response compared to the correct response.







    Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact



    Search:
    联系我们 contact @ memedata.com