Readit NewsQ: how do I change my name in the app?
A few comments from the 20min trial I had:
- About the positive aspects: There were definitly parts of the conversation where I was genuinely suprised with the naturalness. Overall, I felt that the demo already helped me practice my output a bit. From this, I definitely believe that AI-based language tutors might become quite widespread soon as they could become really good language exchange partners. In my case, I still have low speaking skills (~Japanese N4, A2), so just having any chance to practice verb conjugations etc is already immensily helpful.
- I also like that there is no gamification aspect. I prefer apps where users can decide how they use them. A lot of Japanese learners, people already use anki for vocab, etc., so forcing extra vocab practice would me definitly quit the app.
Some feedback for improvement:
- Due to my still low speaking skills, I often need mid-sentence pauses which are at least 1-2 seconds long. When I pause, the sentence is already half-transcribed, sometimes in another language. I think I had moments where then the sentence is cut-off entirely. At least, it makes me pressured to finish the sentence in a fluent manner without much pauses.
- I know you want to have multilingual transriptions, but maybe you could add some language bias in transcribing the speech?
- About the cutting off: If you have some sort of VAD frontend: Maybe you could adjust its parameters based on estimated language skills of the users (beginners have longer pauses)
- I saw that my sentences were rated. But they were rated only in text, even though I said that my mistakes should be corrected right away (The speech-based AI partner just kept on talking about the topics). Maybe I have overlooked something, but is there some overview of my mistakes besides the text-based corrections?
1. The response latency / patience can be configured in the quick settings (tap the gear during the call).
2. There already is a bias in transcription. It's something we're actively improving, multilingual transcription isn't a solved problem yet
3. It is supposed to correct you actively if you have corrections enabled (check the settings). But we received feedback that it's not enough, so we will ramp it up soon
But how do you know the furigana are correct? Unless you start out fully human-annotated text, you need some automated procedure to add furigana, which pushes the problem from "TTS AI picked the wrong reading" to "furigana AI picked the wrong reading."
Also Japanese specifically has this meme where it literally is a pitch-accent language but many people say it's not and teaching resources ignore it. E.g. 'ima' means either 'now' or 'living room' depending if syllable #2 is higher or lower. Clearly only applies to some languages, but is another dimension even harder to a learner to know there's a mistake. I have to imagine even other Latin languages probably have reading quirks where this could happen to me.
There are incorrect reading or Chinese readings occasionally, but you can tell when that happens due to the furigana being different
The app also used a bunch of constructions I’m not familiar with even though I specified I’m a beginner.
If I hired a human tutor and had this experience, I would ask for my money back.
We are aiming to create a long term companion/tutor that gets to know you more and more, and can create customized curriculums, lessons, etc.
Also, having the AI voice tutor as our main feature allows us to iterate quickly, and be well positioned for future improvements in AI models.
As for marketing and GTM, we're in the super early stages, and there is definitely a lot of competition out there, it won't be easy.