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.

How SDP works

SDP stands for Session Description Protocol. It is used during WebRTC setup to describe what media a session can send and receive, including codecs, tracks and connection details.

In a real-time avatar session, the browser and the avatar service exchange SDP offers and answers before media starts flowing. That negotiation tells both sides how audio and video should be handled.

A concrete example: the client creates a WebRTC offer, sends it to the avatar API, and receives an SDP answer that allows the browser to connect to the live avatar stream.

Most builders do not need to hand-write SDP, but it is useful to recognise the term when debugging connection setup. If negotiation fails, the avatar may never start streaming even though the API call succeeded.

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

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.

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.

Avatar API

An avatar API is a developer interface for creating, configuring, and streaming interactive digital characters inside an application, so products can start live avatar sessions, pass user input to an agent, and return spoken video responses in real time.

Frequently asked questions

What is SDP used for in WebRTC avatars?

SDP describes the media session, including codecs, tracks, network candidates, and capabilities, so the browser and avatar service can agree how to send audio and video.

Why do developers see SDP during avatar setup?

WebRTC uses an offer and answer exchange to negotiate the session. SDP is the structured description passed between the client and server during that setup.

Do teams usually need to edit SDP manually?

Usually no. SDKs and WebRTC libraries generate SDP for you, but understanding it helps when debugging codec support, connection failures, or unexpected media behavior.

What can go wrong with SDP in avatar sessions?

Mismatched codecs, missing tracks, bad candidates, or incorrect negotiation can stop the avatar stream from connecting. These issues often show up before media starts playing.

Last updated: 17th July 2026 · Reviewed quarterly.

← Back to glossary