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

151–160 of 182 posts

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

#151

Post by reissbaker »

yanyan_evie wrote: post #141
standapart wrote: post #140

I forgot that we're playing the demo games now. Well I'll see your demo, and raise you another demo https://x.com/sean_moriarity/status/1760435005119934862 Except that demo was done by a single person, with a day job and no cap table.

Love to see people has interest over our demo. But, I checked his former post, and he already built a voice Agent a couple of days ago. So I believe he just changed the prompts to create this demo: https://twitter.com/sean_moriarity/status/175895035375034804... . Also, after testing their live demo at https://nero.ngrok.dev/ , it appears it might still be missing some key features, such as latency and endpoint detect…

As a bystander, I definitely agree that Retell's demo wins on latency — it felt pretty close to human. The voice also sounds more natural to my ears (not sure why, since Nero is apparently using Eleven Labs for voices, and Eleven's voices usually sound pretty good to me).

Playing around with the Nero demo, it also feels pretty... broken? I never actually managed to make a booking with Nero; it seemed to often not be able to tell I was done speaking, and would just hang after a couple back-and-forths. Still impressive for a one-man demo built quickly, but they don't feel in the same league.

I do wish Retell's pricing was cheaper, though; $6/hr is pretty much the cost of a call center employee in India, and LLMs still perform below the average human on most things. That being said, I imagine the cost of Retell will come down as the tech advances, and LLMs will also improve over time.

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

#153

Post by lawrencechen »

yanyan_evie wrote: post #145
lawrencechen wrote: post #144

Can you buy/remove phone numbers programmatically? I can't find anything in the docs.

We have an open-source demo repo: Node.js demo: https://github.com/adam-team/retell-backend-node-demo Python demo: https://github.com/adam-team/python-backend-demo

thanks!

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

#154

Post by kiney »

yanyan_evie wrote: post #107
nsokolsky wrote: post #101

The demo is nice but it makes me wonder: why would a company have a fully automated voice line rather than a booking interface? As a customer I'm never happy to call a company to make a reservation. I'd be extra annoyed if an AI picked up and I had to go through the motions of a conversation instead of doing two clicks in a Web UI.

Yes, for booking appointments, a simple interface might do the trick. However, we've seen many excellent use cases of our API that prevent repetitive tasks and help companies save money, like AI logistics assistants, pre-surgery data collection, AI tutor and AI therapists. I believe the future will bring even more voice interface applications. Imagine not having to navigate complex UIs; you could easily book a flight…

Booking a flight with a voice interface is 10 steps backwards from web UIs where I can see different options, prices, calendars....

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

#156

Post by yanyan_evie »

jsumrall wrote: post #155

First thought is can’t you set up calls with prospects and have the product _literally_ sell itself?

Great idea. However, it seems like outbound sales calls could be annoying, and the FCC appears to restrict them.

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

#157

Post by iraldir »

- Did not work on firefox for me (start conversation and nothing would happen, I would not hear the voice) - on chrome it would not allow to change my microphone so had to open my macbook. - Also on firefox, when I first logged in, clicking on he "try now" button would send me back to the landing page, I had to go and click on the playground

With that out of the way, it's really interesting. The challenge I suppose is how narrow / wide the API made by the developer is. A narrow case, like "booking a dentist appointment", might feel like a step down compared to an online form, and most likely would fail short of satisfying someone calling, because if they're calling they had some deeper needs.

On the other hand, a wide API, like if you gave access to pricing information of the dental practice, info about the doctors, a way to reach an actual human being, health advice and post op advice, generate documents from past appointments etc, and you have a higher chance of hallucination, misclassification of what the user wants etc.

I'm still not sure if the best approach is just to leave the AI to deal with that, or to represent the user intent etc. with some sort of State Machine. Maybe a case by case etc. But the more you add in that logic, the slower the machine is.

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

#158

Post by AmuVarma »

russ wrote: post #133
russ wrote: post #115

Earlier quoted context omitted.

We recently made it a lot easier to build your own KITT too: https://github.com/livekit/agents

But we don't handle interruptions yet, that's some cool stuff @yanyan_evie!

There are a lot of good VAD open source models that are easily configurable, and can be integrating in a day or 2 - checkout the silero vad model

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

#159

Post by seanmor5 »

reissbaker wrote: post #151
yanyan_evie wrote: post #141

Earlier quoted context omitted.

Love to see people has interest over our demo. But, I checked his former post, and he already built a voice Agent a couple of days ago. So I believe he just changed the prompts to create this demo: https://twitter.com/sean_moriarity/status/175895035375034804... . Also, after testing their live demo at https://nero.ngrok.dev/ , it appears it might still be missing some key features, such as latency and endpoint detect…

As a bystander, I definitely agree that Retell's demo wins on latency — it felt pretty close to human. The voice also sounds more natural to my ears (not sure why, since Nero is apparently using Eleven Labs for voices, and Eleven's voices usually sound pretty good to me). Playing around with the Nero demo, it also feels pretty... broken? I never actually managed to make a booking with Nero; it seemed to often not be…

Yeah the latency in my demo is definitely worse. There also seem to be some issues where it picks up it’s own audio and keyboard/mouse clicks and tries to transcribe them which leads to derailed convos.

The unnatural voices happen I think because for some reason the way I stream audio to the browser breaks up the audio from ElevenLabs, so you get almost this “start/stop” sound that makes it sound worse than usual.

There’s a lot of minor details to get right, but it’s a fun problem to try to solve. I wish Retell the best :)

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

#160

Post by Spiwux »

I'm assuming you're targeting this mainly at enterprises and business use-cases such as callcenters, but are you planning to make this usable for personal use cases as well? For example, having a bot to bounce ideas off while coding. Pretty much "just" the TTS / STT layer to talk to my finetuned LLM in a natural manner while you handle interruptions and such.

I think the main issue right now for personal use would be cost (and I'm guessing STT / TTS are the most expensive parts..)

Post reply on HN