Skip to main content

​
Telnyx Voice: Overview — Full Documentation

Complete page content for Overview (Voice section) of the Telnyx developer docs (https://developers.telnyx.com). This file: https://developers.telnyx.com/docs/development/llms/voice-overview-llms-full-txt.md · Root index: https://developers.telnyx.com/llms.txt

​

​
Overview

Source: https://developers.telnyx.com/docs/voice/overview.md
The Telnyx Voice platform provides a complete set of APIs and SDKs for building real-time voice applications. Built on a private global IP network spanning 20+ points of presence, every voice product runs on Telnyx-owned infrastructure — from SIP trunking and programmable call control to browser-based calling and AI-powered voice agents.

​
Key capabilities

  • Inbound and outbound calling — Route and manage calls with granular control over every leg of the conversation.
  • Call Control — A REST and webhook-based API for programmatic call management: answer, transfer, bridge, conference, record, gather DTMF, and play audio.
  • IVR and call routing — Build interactive voice response menus, queue calls, and route to agents or departments.
  • Recording and transcription — Record calls on demand and transcribe them with multiple STT engine options.
  • Conferencing — Create multi-party conference calls with muting, hold, and moderator controls.
  • Answering Machine Detection — Detect voicemail vs. live answer to optimize outbound campaigns.
  • AI-powered voice — Integrate speech-to-text, text-to-speech, and large language models directly into call flows.

​
Products

Connect your existing PBX or communications infrastructure to the Telnyx network with elastic SIP trunking. Control calls in real time with the Call Control API — answer, transfer, record, conference, and more. Add browser and mobile calling to your application with the Telnyx WebRTC SDK. Build AI-powered voice agents that handle real phone calls with ultra-low latency. Real-time and file-based transcription with four engine options: Telnyx, Google, Deepgram, and Azure. Convert text to natural-sounding audio via WebSocket streaming. Multiple voice providers and languages. Clone voices from audio samples or design custom AI voices from natural language prompts.