Every AI conversation resets. Velur doesn't. It's a voice-first AI companion with persistent memory. Talk to it like a phone call — real-time voice streaming, not text-to-speech — and it remembers everything across sessions. Your name, your interests, what you said last week. The more you talk, the better it knows you. 7-day free trial, no card required.
No reviews yetBe the first to leave a review for Velur
Maker
📌
Hey everyone — I'm Shubham, solo founder of Velur.
I built this because every AI conversation feels like talking to someone with amnesia. You share something important, come back the next day, and it's completely forgotten.
Velur remembers. You mention a job interview on Monday, it asks how it went on Thursday — without you bringing it up.
I'm an MBA and AI engineer. Built the entire stack solo — real-time voice streaming, persistent memory engine, frontend, backend, payments.
Would love your honest feedback. What works, what doesn't, what would make you use this daily.
Report
Maker
Quick note on how the memory works — Velur doesn't just store chat logs. It extracts specific facts from your conversations (your name, interests, what's happening in your life) and recalls them naturally in future sessions. It's not keyword matching, it's semantic search over everything you've ever shared.
Report
Looks interesting, best wishes. What are some of use-cases of this applications that you are seeing most used by users ?
Report
Maker
For anyone curious about the voice quality — this isn't text-to-speech layered on a chatbot. It's real-time bidirectional voice streaming through AWS Nova Sonic. You talk, it listens and responds simultaneously, like an actual phone call. Latency is low enough that it feels natural.
Quick note on how the memory works — Velur doesn't just store chat logs. It extracts specific facts from your conversations (your name, interests, what's happening in your life) and recalls them naturally in future sessions. It's not keyword matching, it's semantic search over everything you've ever shared.
Looks interesting, best wishes. What are some of use-cases of this applications that you are seeing most used by users ?
For anyone curious about the voice quality — this isn't text-to-speech layered on a chatbot. It's real-time bidirectional voice streaming through AWS Nova Sonic. You talk, it listens and responds simultaneously, like an actual phone call. Latency is low enough that it feels natural.