thanks for the kind words!! It is built on top of a fairly straightforward infra... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		billylo on Oct 29, 2024 \| parent \| context \| favorite \| on: Ask HN: Real-time speech-to-speech translation thanks for the kind words!! It is built on top of a fairly straightforward infrastructure. Client side is C#, .NET, MAUI. Server side is Firebase Cloud Functions/Firestore/Web Hosting + Azure.

supermatt on Oct 29, 2024 [–]

Thanks - I was wondering more about the translation pipeline - i am assuming something like whisper and m2m100? How did you manage to get the latency so low? Other examples I have seen feel really sluggish in comparison.

billylo on Oct 29, 2024 | [–]

Fairly basic there... chunking audio (websocket) and send them for translation sequentially.

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