Live data from Hacker News

Show HN: Production duplex speech model for revenue calls

metavoice.io

1–3 of 3 posts

Show HN: Production duplex speech model for revenue calls

#1
Hi, HN, we’re building Mia & Leo: AI personalities backed by purpose-built duplex speech models for revenue calls.

Teams building real-world agents told us that more than 40% of callers hang up within the first 30 seconds. On a revenue call, that meant a lost booking, an unpaid balance, a cold lead, or a customer who does not come back.

This happens because humans interrupt, correct dates, pause halfway through a sentence, or speak over someone in the background. The agent misses it, talks over them, or loses the thread.

That’s because of how the current voice systems work. They sequentially listen, stop, think, and then speak. The conversation is actually a walkie-talkie exchange.

So, we’re proud to introduce our first iteration of Mia & Leo who keep listening while they speak. They can handle interruptions, overlapping speech, corrections, and background voices without breaking the conversation.

They are also built for production. Developers get control over agent behaviour, visibility into calls, failures they can debug, and costs that work at scale.

Please try them out at metavoice.io. We'd love to hear any feedback!

Show HN: Production duplex speech model for revenue calls
metavoice.io

Re: Show HN: Production duplex speech model for revenue calls

#3
post #2

enjoyed testing out Leo & Mia. Exciting mission - wondering what the benchmarks are like?

glad to hear it!

> wondering what the benchmarks are like?

we've avoided OS benchmarks as they don't quite represent the scenarios and problems our customers face.

we instead developed an internal eval set that more closely represents our customers workflows / domain.