Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Retell AI (YC W24) – Conversational Speech API for Your LLM

news.ycombinator.com

Post reply on HN
Print view View original

171–180 of 182 posts

Re: Launch HN: Retell AI (YC W24) – Conversational Speech API for Your LLM

#171

Post by arrowoftime »

yanyan_evie wrote: post #89
zachbee wrote: post #86

What's the difference between your product and Gridspace's? I get the sense that your offering is more developer-focused, but I'm curious if there are any technical differences.

I believe Gridspace is an IVR solution, not one based on LLM. It's challenging to ask questions that deviate from the initial settings. We're using LLM to generate responses, which makes the conversation smoother.

Gridspace’s lecture series on building / extending LLM’s for MIT IAP: https://youtube.com/playlist?list=PL6owWFYBB-AqnqbfPOudH3xGu...

Re: Launch HN: Retell AI (YC W24) – Conversational Speech API for Your LLM

#174

Post by user_7832 »

ywj7931 wrote: post #57
user_7832 wrote: post #55

It's really good, but the AI cracks still show up. Trying the demo therapist, I mentioned I'm not finding a job. It suggested finding a career counsellor and said "it would get back as soon as possible"... yeah, no it didn't. It claimed to be "working on it" but would say "I'm here if you want to speak...". It clearly doesn't understand what it's saying, it feels like bing's ai would be "better" at not claiming to do…

Thanks for trying that out! Retell focuses on making the AI sound like human, it is developers' LLM responsibility to make it think smart. The therapist in the dashboard is for demo purpose only and ideally some developers will plug in their great AI therapist LLM to make it more human-like :)

Thanks for the clarification! It appeared that the LLM was part of your product/service but if it can be changed by the devs that's good!

Re: Launch HN: Retell AI (YC W24) – Conversational Speech API for Your LLM

#175

Post by mvkel »

staplar wrote: post #131
JustinGu wrote: post #87

Wow this is incredible. I've worked a bit in the conversational LLM space and one of the hardest problems we were struggling with was human interruption handling. From the demo it seems like you guys have it down. Can't wait to see where this goes :) BTW I don't think the demo works on mobile, tried it on safari on IOS and got no response.

They're most likely have two "agents" working in tandem to listen and speak, and it seems like the listener takes precedence over the speaker agent but underneath they share the same context window. Programming wise, probably using multithreading and channels architecture, depending on the programming language.

What a cool trick to pull that off!

Re: Launch HN: Retell AI (YC W24) – Conversational Speech API for Your LLM

#176

Post by sanchitv »

yanyan_evie wrote: post #173
sanchitv wrote: post #172

Excellent product and fantastic demo! Would it be possible to integrate Retell with a RAG pipeline?

Yes, certainly can. We give the maximum customization for the LLM part.

Perfect, thanks for the follow-up!

Re: Launch HN: Retell AI (YC W24) – Conversational Speech API for Your LLM

#179

Post by benkaiser »

This really makes me wonder if we can go full circle at fast-food restaurants like McDonalds. Ordering at a counter (10 seconds) has been replaced in recent years with touching a giant screen (2+ minutes).

This demo really shines light on how you could "talk" to place your order in a comparatively fast amount of time, similar to speaking with a human. Yes it can't handle all the million corner cases, and it will get it wrong a bunch of the time, but at least you can verify your order on a screen before tapping your phone to pay.

Post reply on HN