Odyssey API (interactive world model video)

Overview

Best for: Interactive storytelling, prototypes and demos of playable AI video.

At a glance

Streams end after 150 s by default; connections max 60 min. Concurrency 5 is the free tier. No published pricing. Resolution and fps (20-22) are third-party reports.

Features

• text-to-interactive-video
• image-to-video start frames (resized to 1280x704)
• interact() mid-stream prompts
• broadcast/viewable streams
• async simulation jobs
• short-lived session JWTs for browsers

Pricing

Free tier: Free accounts get 5 concurrent streams; hour quota not published.

Source: documentation.api.odyssey.ml

Setup

1. Get an API key at developer.odyssey.ml.
2. npm install @odysseyml/odyssey.
3. connect() to get a MediaStream, attach it to a video element.
4. startStream with a prompt, interact() to steer, endStream() and disconnect() when done.
5. Mint session JWTs server-side for browser use instead of exposing the key.

Endpoint

@odysseyml/odyssey SDK (WebRTC + WebSocket signaling)

Authentication

API key (ody_...) or short-lived session JWT

import { Odyssey } from "@odysseyml/odyssey";

// Use a server-minted session credential in production, not the raw key
const client = new Odyssey({ apiKey: "ody_your_api_key_here" });

const mediaStream = await client.connect();
document.querySelector("video").srcObject = mediaStream;

await client.startStream({ prompt: "A cat on a sunny windowsill" });
await client.interact({ prompt: "Pet the cat" });
// each stream lasts max 150 s by default
await client.endStream();
client.disconnect();

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

Warnings

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

Limits

• Each stream max 150 s by default (start a new stream to continue)
• Each connection max 60 min
• Idle connection with no active stream disconnects after 15 min
• Up to 10 queued simulation jobs
• Total streaming hours capped by account quota

Models and products

Docs and sources

Docs

• API quick start
• Stream duration limits
• Session management

Sources used

• documentation.api.odyssey.ml/session-management.md
• documentation.api.odyssey.ml/stream-duration-limits.md
• documentation.api.odyssey.ml/api-quick-start.md
• odyssey.ml/the-gpt-2-moment-for-world-models
• odyssey.systems/