The team wanted an in-car assistant that could answer questions and control app features by voice, but building automotive-grade voice was a multi-quarter project.
They needed a working prototype fast to validate the idea.
The solution
The team embedded voice into their own app via the MyChatBot Web Voice SDK:
Voice inside the app, the MyChatBot Web Voice SDK adds inbound (WebRTC) and outbound (Twilio/SIP) calls with a few lines of JS.
Own voice and instructions, each AI voice agent gets its own voice, language and prompt, fully under the team's control.
Client-side tools, the agent calls the app's own functions mid-call, navigating the UI, searching, booking, updating records.
Persistent callers, defaultCallerId keeps a stable identity across sessions, so context follows the user.
Scales with usage, minute bundles and per-minute overage mean the same SDK serves a prototype and a production app.
Using the SDK and client tools, a working in-car assistant was prototyped in days.
What was deployed
Agents used
Voice Agent (SDK)Client Tools
Channels connected
Web Voice SDKWebRTCTwilio/SIP
"We validated a real in-car voice assistant in days, not quarters."
Yuriy Bondar
Platform Lead
Ship something like this
Set up your first AI agent in 10 minutes. Plans and trial terms on the pricing page.
