What's actually breaking in your voice agents right now?
Everyone's shipping voice agents this year. Receptionists, collections bots, lead qualifiers, support lines. The demos look great.
Then they hit a real phone call.
I lead growth at a voice AI company, so I sit in on a lot of these conversations. And the thing that surprised me is how rarely the LLM is the problem. It's almost always the voice layer underneath it. The latency that was 90ms in the demo, suddenly climbs to 400ms on a real phone call. The voice that sounds great in English and falls apart the moment someone switches to another language mid-sentence. The TTS that reads a pincode like a phone number. Or the per-minute bill that was fine at 10,000 minutes and became the biggest line item at a million.
If you're building voice agents, what's the one thing that still breaks in production?
And for the people picking vendors:
What do you actually look at when you choose a TTS provider? Speed, sound, price, languages, or something nobody benchmarks?
We are about to launch something exciting tomorrow!
Replies
were not doing live calls so latency doesnt bite us, we use tts for video narration. but the pincode thing u mentioned is exactly our problem too.
product names are the worst. anything capitalised or with a number in it gets read as letters or as a year, and u only find out on playback. thats the thing i check first now and ive never seen it on a comparison page.
@niveditha_patluri1 This is exactly the pain point we are addressing with Murf Falcon 2. You do not need to choose between latency, naturalness or price no matter what the use case may be. We are launching today, check it out here!