Launch a custom Voice AI product
Real-time STT, LLM and TTS orchestration, tool calling, barge-in, call control and structured post-call data.
FROM PROTOTYPE TO OPERABLE SYSTEM →● AVAILABLE FOR SELECT PROJECTS
VOICE AI / SIP / WEBRTC
I help product teams launch, scale, or rescue real-time voice systems — from SIP, WebRTC and FreeSWITCH to low-latency STT, LLM and TTS pipelines.
REPLY WITHIN 1 BUSINESS DAY · NO SALES HANDOFF · REMOTE WORLDWIDE
HOW I CAN HELP
I can own the voice layer end to end, join an existing engineering team, or diagnose the narrow production issue blocking a launch.
Real-time STT, LLM and TTS orchestration, tool calling, barge-in, call control and structured post-call data.
FROM PROTOTYPE TO OPERABLE SYSTEM →One-way audio, latency, dropped media, broken signalling, VAD failures and demos that collapse under real traffic.
DIAGNOSIS, FIX AND VERIFICATION →SIP routing, WebRTC, SBCs, NAT traversal, carrier integrations, redundancy, observability and high concurrency.
ARCHITECTURE YOUR TEAM CAN OPERATE →SELECTED WORK
Representative projects across Voice AI, browser telephony and telecom infrastructure.
NEED A controllable media layer and production deployment for a high-volume AI calling product. DELIVERED Drachtio and FreeSWITCH orchestration, Kubernetes deployment, speech pipeline integration and barge-in behavior.
A controllable media layer and production deployment using Drachtio, FreeSWITCH, Kubernetes and a real-time speech pipeline.
DRACHTIO · FREESWITCH · NODE.JS · KUBERNETES · DEEPGRAMNEED Release the human agent immediately while a prerecorded voicemail continues playing. DELIVERED Embedded WebRTC softphone, early-media handling, backend state control and reliable media handoff.
Embedded WebRTC softphone, early-media handling and backend state control that releases the agent while playback continues.
WEBRTC · FREESWITCH · SIP · NODE.JS · REDISCLIENT FEEDBACK / UPWORK
“Soslan fixed our voice AI agent issues quickly and professionally. He resolved the WebSocket latency, VAD problems, and barge-in functionality within a few days. Fast, reliable, and knows his stuff.”UPWORK CLIENT · PRODUCTION FIX
“Fantastic to work with. Very communicative and responsive, wrote clean code, and helped go back-and-forth with me to get the work I needed done well.”UPWORK CLIENT · REPEAT WORK
“He understood the brief and executed it to perfection. Would hire again.”UPWORK CLIENT · 10/10
“Excellent communication and professionalism. This is our second time working together.”UPWORK CLIENT · 02 PROJECTS
“Clean documentation, smooth deployment, and highly accountable for outcomes.”UPWORK CLIENT · DELIVERED
ABOUT
I’m a backend and VoIP engineer with 15+ years of experience building telecom infrastructure and real-time systems. You work directly with me — from architecture and call flows to production debugging and deployment.
START A CONVERSATION
Send the current architecture, call flow or production symptom. I’ll reply with the questions needed to identify the shortest path forward.
COMMON QUESTIONS
Yes. Most engagements start inside an existing SIP, WebRTC or Voice AI system rather than from a blank slate.
No. I can own architecture and implementation, or join your team for a focused production problem.
A simple call flow, current stack, expected volume and the main failure or outcome you are trying to reach.