Avatars Now in Beta for Telnyx Voice AI Assistants

13, Oct 2026

Telnyx AI Assistants can now appear on video. Six preset avatars, rendered by a model that runs on Telnyx infrastructure, are available in beta.

What's new

  • Six preset avatars: Choose elena, ben, jordan, lin, avery, or raphael, each with a selectable background: office, studio, or reception. Custom avatars are coming soon.
  • Opt-in per conversation: Avatar settings are saved on the assistant, and each conversation opts in with avatar=true. Saving an avatar doesn't turn every conversation into a video session.
  • Telnyx-hosted rendering: The avatar model runs on Telnyx infrastructure, so audio and video stay on the same network instead of adding a third-party service to the path.
  • Built-in voice fallback: If the avatar hits a runtime error, the conversation falls back to voice-only audio and keeps going.
  • Telnyx TTS required: Avatar conversations work with Telnyx-provider voices only. Third-party TTS, including ElevenLabs, is not supported, including Portal tests.
  • Pricing: Included in AI Assistant call pricing through October 2026. From November 1, 2026, avatar usage costs $0.08 per minute, in addition to standard AI Assistant call charges.

Why it matters

Adding a face to a voice agent used to mean adding a vendor: a third-party avatar service sitting between your assistant and the caller, with its own API, its own latency, and its own contract. The avatar model runs on Telnyx infrastructure instead, next to your assistant's voice, transcription, and tools. Video becomes a setting on the assistant you already have, not another integration to maintain. One assistant, one control plane, audio and video on the same network.

Example use cases

  • Support teams: put a face on the assistant answering questions in your web or mobile app, with an office or reception background.
  • Patient intake: give patients a consistent, friendly face for appointment booking inside a patient portal.
  • Landing pages and product tours: let visitors talk to an on-screen agent without wiring up a separate video vendor.
  • Lobby kiosks and front desks: run an interactive avatar for check-in and wayfinding.

Getting started

  1. In the Mission Control portal, open AI, then Assistants, select your assistant, and configure the avatar: pick an avatar, a background, and a Telnyx voice.
  2. Or set avatar_settings when creating or updating an assistant through the API:
{
  "avatar_settings": {
    "provider": "telnyx",
    "model": "foxtrot-1",
    "avatar_id": "elena",
    "background_id": "studio"
  }
}
  1. Start an avatar conversation over the conversation WebSocket with avatar=true; video is delivered over WebRTC. Complete the avatar setup within 60 seconds of connecting.

Learn more in the Avatars docs.