WebRTC

WebRTC is the browser standard for low-latency live audio and video streaming, commonly used to carry microphone input and avatar output during real-time interactive sessions.

How WebRTC works in avatar sessions

WebRTC is a browser standard for low-latency audio and video communication. It is designed for live media, which makes it a natural fit for real-time avatar sessions.

In an avatar product, WebRTC can carry the user's microphone audio to the avatar service and stream the avatar's video and voice back to the browser. It supports the kind of two-way media flow that a normal video file cannot provide.

A concrete example: a user opens a support page, grants microphone access, and connects to an avatar over WebRTC. The session stays open while the user and avatar take turns speaking.

WebRTC matters because the category is live. If the experience is delivered as a rendered file or a high-latency video stream, it cannot support the same interruption, turn-taking and conversational feel.

Response time

User experience

What Anam ships

Anam's Cara-4 model delivers expressive real-time avatars with around 150 ms server-side avatar-generation latency once a session is running, across 70+ languages. Builders use JavaScript and Python SDKs or integrations for LiveKit, Pipecat, ElevenLabs Agents, Agora, and VideoSDK. Bring any AI stack including OpenAI, Claude, Gemini, Mistral, Groq, Deepgram, Cartesia, or custom providers. The platform supports WebRTC delivery, SOC 2 Type II, HIPAA, zero data retention, and regional data residency. Sessions stream low-latency audio and video to browsers and native apps.

Explore the real-time avatar API →

Related terms

SDP

SDP, or Session Description Protocol, is the WebRTC setup format that describes media tracks, codecs, and connection details so a browser and avatar service can start a live stream.

Sub-second latency

Sub-second latency is the end-to-end response time under one second between a user speaking and an avatar replying, covering speech recognition, model reasoning, speech synthesis, animation, and network streaming.

Latency budget

A latency budget is the total response-time allowance split across speech recognition, model reasoning, tools, text-to-speech, rendering, and streaming so a real-time avatar can stay conversational.

Real-time avatar

A real-time avatar is a photorealistic digital character that listens, thinks, and speaks back inside a live audio and video stream, typically with sub-second response latency, so it can hold a two-way conversation rather than play a pre-rendered clip.

Frequently asked questions

Why do real-time avatar APIs use WebRTC?

WebRTC is built for low-latency, two-way audio and video. That makes it a natural fit for avatars that need to listen, speak, and stream face animation live.

How is WebRTC different from normal video playback?

Normal video playback usually delivers a file or stream in one direction. WebRTC keeps an interactive session open so audio, video, and sometimes data can move both ways in real time.

Does WebRTC carry both voice and video?

Yes. A WebRTC session can carry microphone input, avatar video, generated audio, and data channels depending on how the product is designed.

What should developers test with WebRTC avatars?

Test browser permissions, mobile support, network restrictions, TURN fallback, reconnection, media quality, and latency under real-world conditions rather than only on a local connection.

Last updated: 17th July 2026 · Reviewed quarterly.

← Back to glossary