GA D-ID

D-ID Agents (realtime streams)

D-ID's realtime talking-head agents, now built on its V4 Expressive model. Agents Streams V2 runs on LiveKit; there is a client SDK and an embed script.

Est. per minute$0.35 - 0.45

2 high-severity warnings

Overview

Best for: Marketing and training sites that want an embeddable expressive agent with minimal backend work.

At a glance

Session $/min$0.35

Entry plan $/mo$14.4

Free tierYes

Custom avatarYes

Latency ms500

WebRTCYes

Self-hostNo

Open weightsNo

Latency is vendor claim (sub-0.5 s turns); a developer measured about 2.1 s before video starts. Plan prices are third-party: Build $14.40/month (annual, personal use only), commercial from Launch $35. Price is Scale $138.60/400 min.

Audio in

User speech or text chat via SDK

Audio out

D-ID managed TTS / voice clones

Languages

Not verified in this pass.

Latency

Vendor claim: sub-0.5 s conversational turns (V4). One developer forum report measured about 2.1 s extra before video starts in the browser.

Regions

Not verified.

Compliance

Not verified in this pass.

Features

managed LLM agent with knowledge base
LiveKit SDK path for backend orchestration
embed script with no backend
expressive sentiments
custom avatars

Pricing

What	Price	Unit	Notes
Trial	$0	trial	Up to 10 streaming minutes (third-party reproduction of API table)
Build	$14.40	per month (annual)	64 credits, up to 32 streaming minutes, personal use only
Launch	$35	per month	180 credits, up to 90 streaming minutes; commercial use starts here
Scale	$138.60	per month	800 credits, up to 400 streaming minutes
Enterprise	Custom		Concurrency and fastest processing appear to be enterprise features

How the per-minute estimate was worked out

Scale $138.60/400 streaming min = $0.35 to Build $14.40/32 = $0.45; streaming shares the same credit pool as offline video. Third-party data, unverified.

Free tier: Trial allowance (reported up to 10 streaming minutes).

Source: creatify.ai

Setup

Create an agent in D-ID Studio and copy its agent ID.
Backend: POST /agents/client-key with your allowed_domains to get a client key.
Frontend: npm install @d-id/client-sdk and create an agent manager with the client key.
Call connect(), then chat()/speak(), and disconnect() when the user leaves.

Endpoint

POST https://api.d-id.com/agents/client-key

Authentication

Authorization: Basic <API key> on the server; client key in the browser

Quick start javascript

// Browser, after your server created a client key via
// POST https://api.d-id.com/agents/client-key
import * as did from "@d-id/client-sdk";

const video = document.getElementById("agent-video"); // autoplay playsinline
const agent = await did.createAgentManager("agt_abc123", {
  auth: { type: "key", clientKey: CLIENT_KEY },
  callbacks: {
    onSrcObjectReady(stream) { video.srcObject = stream; },
    onConnectionStateChange(state) { console.log("state", state); },
    onNewMessage(messages) { console.log(messages); },
  },
});

await agent.connect();
await agent.chat("Hello! What can you help me with?");
// ...
await agent.disconnect(); // stop billing

Written from the current docs. Check the vendor's SDK version before you ship.

Warnings

Official API pricing page did not render

d-id.com/pricing/api returned only navigation to our fetcher; plan numbers here come from a third-party reproduction. Confirm in the D-ID dashboard.

Cheapest plans are personal-use only

Per the third-party API table, Trial and Build carry a personal-use licence; commercial API use starts at Launch.

Streaming eats the same credits as video

Streaming minutes are drawn from the same credit pool as offline renders, so the 'up to N streaming minutes' figures are not additive.

Measure latency yourself

Vendor claims sub-0.5 s turns, but a developer reported about 2.1 s before playback starts. Test end-to-end in your own stack.

Two stream APIs

V2 (LiveKit) only works with Expressive Agents; other agents still use V1 WebRTC endpoints. Do not mix tutorials.

Plus 9 warnings that apply to all avatars and live video APIs. See category warnings.

Limits

Concurrent stream limit per plan not published (enterprise feature per third-party guide)
Credits do not roll over (third-party)
Client keys are restricted to allowed_domains

Models and products

Name	Status	Notes
V4 Expressive Visual Agents	GA	Launched 16 Mar 2026; diffusion-based, sentiment-aware expressions. Vendor claims sub-0.5 s conversational turns and up to 4K output.
Agents Streams V2 (LiveKit)	GA	Only for Expressive Agents; commands and events over the LiveKit data channel.
Agents Streams V1 (WebRTC)	GA	Used by other agent types; SDP/ICE exchange via REST.

Docs and sources

Docs

Sources used

Not fully verified

All plan prices and streaming-minute allowances (third-party), concurrency, languages, session limits.

Similar avatars + video APIs

TavusTavus Conversational Video Interface (CVI)$0.24 - 0.37/min2 high-severity warnings RunwayRunway Characters (GWM-1 Avatars)$0.20 - 0.22/min0 high-severity warnings AnamAnam$0.11 - 0.24/min1 high-severity warnings DecartDecart Realtime (Lucy)$0.60 - 2.40/min1 high-severity warnings

Spotted a wrong price or a dead link?