@shanaygaitonde@retellai We trained it to do first answer if confident, so this scenario is rare. but when it does find it wrong, it can correct itself, just like how human corrects themselves in a conversation
@tfmlab@retellai Correct this is one of the core areas that we train on and evaluate as well. Benchmarking results take that into account, feel free to check more results at https://t.co/rei4zzhZFq
We’re also introducing Tell-1, our own LLM built for contact centers.
Callers interrupt, give partial answers, and change their minds. The agent still needs to know what to ask and when to act.
Tell-1 thinks while it speaks. Our CTO @zexiazh and Jerry explain how we built it.
Explore the benchmark: https://t.co/NU3GQdOpNA
Retell just crossed $100M in revenue run rate.
$10M to $100M in 17 months. Profitable. $4.6M raised.
From day one, we’ve focused on solving the hardest parts of deploying voice AI in the product itself, so customers can build, manage, and improve their own agents without depending on us.
Our bet: the future of the contact center belongs to the teams who run it.
Proud of our team. Grateful to every customer who believed in us.
.@RetellAI (YC W24) is an API for creating human-like conversational voice AI. Developers can build a voice AI similar to JARVIS in just a day — with an ~800ms response time and the ability to handle interruptions.
https://t.co/rZhdVSr0tE
Congrats on the launch, @zexiazh, @evie_wang0, @yu_weijia, @BingWu772820, and @toddlzt0!