
Video Call Recording has arrived
If a call is made in non-P2P mode then its media stream goes via our media servers and we can record it if required.

If a call is made in non-P2P mode then its media stream goes via our media servers and we can record it if required.

We've started with audio, then we've added video calls and now it's time to let our developers use instant messaging and presence - two very important features of UC stack.

The new version of our mobile SDK uses WebRTC engine for audio/video processing and supports all features available for WebSDK.

Now there is a way to restrict access to VoxImplant HTTP API and only allow it for certain IP addresses or networks when api_key is being used.

Now developers can get phone numbers connected to VoxImplant in more than 40 countries, including United States, United Kingdom, Russia, Argentina, Australia, Austria etc.

All VoxImplant developers can now create/edit/delete Queues and Skills remotely using HTTP API.

We introduced a lot of new features in 2014, but we have even more planned for 2015.

Mozilla recently released Firefox 34 and there were some changes in WebRTC stack that weren't compatible with our Web SDK. We have fixed most of them, p2p video calling will be fixed on Monday.

We are going to provide ready-to-use VoxEngine scenarios, How To's and screencasts.

Video calls support is already available for iOS SDK!

VoxImplant developers can easily embed all functionality VoxImplant offers into their native Android applications.

Transfer a call to another user using Web SDK.

Voximplant now includes a native MCP Client for VoxEngine, giving developers direct connectivity to any MCP server and full control over every tool call

Voximplant now lets developers build full-cascade voice AI pipelines in VoxEngine without sacrificing turn-taking quality.

Voximplant has added a WebSocket privacy option that redacts message payloads from logs across all WebSocket-based services – Voice AI connectors and external speech system – and speech control modules

OpenAI has recently announced GA version of their Realtime API that Voximplant now fully supports

Voximplant now includes a native Cartesia module for streaming, low-latency text-to-speech (TTS). You can use a single VoxEngine API to synthesize speech in real time, connect it to any call (PSTN, SIP, WebRTC, WhatsApp) and control playback from a Large Language Model (LLM) or other source, all inside VoxEngine.

Voximplant now includes a native Deepgram module that connects any Voximplant call to Deepgram’s Voice Agent API for real-time, speech‑to‑speech conversations. You can stream audio from phone numbers, SIP trunks, WhatsApp, or WebRTC into Deepgram’s unified agent environment—combining STT, LLM reasoning, and TTS—and play responses via Voximplant’s serverless runtime with minimal latency.

Voximplant now includes a native Cartesia Line / Agents connector that connects any Voximplant call to a Cartesia Line voice agent for real-time, speech-to-speech conversations—over PSTN, SIP, WebRTC, or WhatsApp Business Calling—without building custom media gateways or WebSocket streaming infrastructure.

Today Ultravox announced they are directly integrating Voximplant into their platform to provide SIP capabilities. The integration builds on Voximplant’s deep telephony and Voice AI tooling