Aiko uses xAI’s Grok (latest model) to craft natural Japanese replies and AWS Polly (Mizuki voice) to speak them. Pick a topic like "Greetings" or "Ordering Food," hit "Click to Record," and talk to her in Japanese—she listens via Web Speech API, responds, and plays it back. It’s real-time, with a mic level visualizer and auto-scrolling chat, all in client-side JS (React + Tailwind).
This ties into my Japanese Complete project (data-driven, 90% real-world Japanese coverage). Sold a $450 lifetime plan this morning, so I figured it’s HN time. Next up: server-side polish, auth, and more topics. Would love your take—especially on UX or scaling ideas!
Also, there are four previous postings under the sova account, so this is not exactly new. Show HN is not for advertising products.
- Aiko: Learn Japanese Effortlessly, with MMLM-Powered Digital Sensei (japanesecomplete_com/aiko-announcement) 2 points | sova | 1 year ago
- Aiko, learn Japanese rapidly with her help (japanesecomplete_com/aiko-announcement) 1 points | sova | 1 year ago
- Aiko: MMLM (Multimodal Language Model)-Powered Digital Sensei for Japanese (japanesecomplete_com/articles/?p=1574) 3 points | sova | 1 year ago
- Aiko – A New Wave in Learning Japanese – AI-Powered Digital Sensei (japanesecomplete_com/articles/?p=1536) 6 points | sova | 1 year ago
If you feel this post has stated the case unfairly, please feel free to contact the HN moderators at the email address in the Guidelines link at the bottom of the page.