Skip to content

Duvo deploys production voice agents in one week with ElevenAgents

Duvo deployed a production-ready voice layer in days instead of 8-12 weeks.

duvo

From first API call to production voice agents in one week - supported by ElevenLabs Startup Grants

Duvo builds AI agents that manage operations end to end, turning conversations into governed, automated workflows. Business users describe a process out loud, and Duvo maps it, identifies gaps, and converts it into a tracked execution assignment with ownership, status, and controls built in. Their system then deploys voice agents that act on those workflows - calling suppliers, confirming delivery dates, collecting documentation, and updating enterprise systems.

Voice is a key part of Duvo's product experience. To power it, Duvo leverages ElevenAgents - moving from their first API call to a production-ready voice layer in one week.

Shipping production voice in one week

ElevenAgents’ configurability allowed Duvo’s engineers to tune latency and streaming behavior, adjust voice characteristics for different enterprise contexts, and integrate voice directly into workflow orchestration without building infrastructure for real-time audio streaming, interruption management, or speech handling.

Instead of spending an estimated 8-12 weeks building and hardening custom speech infrastructure, Duvo deployed a production-ready voice layer in days. This eliminated the need to implement and maintain streaming pipelines, barge-in handling, and speech lifecycle management in-house.

For an early-stage company building a voice-native enterprise product, this removed months of infrastructure work and reduced operational risk. Duvo is also a recipient of the ElevenLabs Startup Grants program, which reduced early-stage cost constraints and allowed them to focus engineering effort on orchestration, governance, and enterprise logic rather than speech infrastructure.

Enabling voice-to-automation for enterprises

Most enterprise operations still depend on human conversations and manual work: calling suppliers, chasing confirmations, collecting documents. These workflows span multiple systems and teams, and they've never been mapped, let alone automated.

Duvo built two products with ElevenAgents to change that.

Duvo Clarity captures how workflows actually operate through structured conversations with the people who run them. In one session with a European grocery retailer, Clarity mapped a promotion setup workflow that spanned five systems and three teams. It found two control gaps and over one million euros in annual margin leaking from delayed supplier confirmations, a problem nobody had documented. That took an afternoon, not the six-to-eight-week consulting engagement it would normally require.

Duvo's autonomous voice agents then act on what Clarity finds. Instead of a buyer spending their morning calling suppliers to confirm delivery dates, the agent makes the calls, collects the confirmations, and writes the results back into the ERP. 

Why ElevenAgents

Rather than stitching together separate Speech to Text, language model, and Text to Speech systems, Duvo integrated ElevenAgents as a unified conversational layer purpose-built for natural sounding conversations. With ElevenAgents, Duvo was able to deliver low-latency voice interactions, handle real-time turn-taking without awkward pauses, iterate on voice style and agent behavior through an API-first workflow, and embed voice directly into orchestration logic rather than treat it as a surface layer.

"The first time a customer talked through their workflow and saw a structured process map come back in minutes, the room went quiet. That's when we knew voice wasn't a feature, it was the interface. ElevenLabs made it possible to ship that experience in a week." – Tomas Cupr, CEO, Duvo

What's next

For teams building AI operators, voice-native enterprise tools, or automation systems that depend on real-time dialogue, building and maintaining a custom speech stack slows execution and increases operational complexity. ElevenAgents allows teams to ship production-grade conversational agents immediately and focus on the product that differentiates them.

To get started, explore ElevenAgents or apply to the ElevenLabs Startup Grants program.

Explore articles by the ElevenLabs team

Create with the highest quality AI Audio