Skip to navigation
Voice AI Clients

Connector Options

Compare connector options and jump into runnable examples.
View as Markdown

For the complete documentation index, see llms.txt.

Choose a connector based on your preferred model provider and feature set. Every connector page includes an overview, architecture notes, and code-first VoxEngine examples.

OpenAI

OpenAI and OpenAI-compatible APIs with direct realtime, full-cascade, and half-cascade voice pipelines.

Inbound | Outbound | Function calling | Full-cascade | Half-cascade

Gemini Live

Gemini live audio sessions with support for direct Gemini API or Vertex AI credentials.

Inbound | Outbound | Function calling | Vertex | Speech translation

Ultravox

Speech-native voice AI with examples for inbound, outbound, and tool-driven interactions.

Inbound | Outbound | Function calling

ElevenLabs Agents

Connect ElevenLabs conversational agents to PSTN, SIP, WebRTC, and WhatsApp call flows.

Inbound | Outbound | Function calling

Cartesia Line Agents

Line-agent runtime pattern for real-time calls, tool handling, and external business logic.

Inbound | Outbound | Function calling

Inworld Realtime

Speech-to-speech sessions with Inworld speech recognition, an LLM, and TTS-2 output.

Inbound | Outbound | Function calling

Deepgram Agents

Deepgram Voice Agent integration with support for context history in ApplicationStorage.

Inbound | Outbound | Function calling

Grok Voice Agent

xAI Grok real-time voice integration with examples for core calls and connector-specific features.

Inbound | Outbound | Feature controls

Qwen Cloud

Direct realtime speech-to-speech with the Qwen audio model, including inbound, outbound, and function calling.

Inbound | Outbound | Function calling

Structured decisions

Jev is not a realtime voice connector. It returns typed answers from text you send in a request, and it does not take call audio.

Jev

TypeSafe System One decisions for routing, triage, and scoring.

Common capabilities across connectors

  • Route calls from PSTN, SIP, WebRTC, or WhatsApp through VoxEngine.
  • Bridge call media to a provider connector in real time.
  • Handle barge-in by clearing connector output when user speech starts.
  • Implement tool/function execution for CRM actions, transfers, scheduling, or custom workflows.
  • Store provider API keys in Voximplant Secrets and keep examples production-safe.