FastH3-Omni overview

FastH3-Omni generates video clips with synchronized audio. Start with text alone, use reference images to shape characters and settings, pin the opening or closing frame with separate keyframe images, or continue an earlier clip. Use up to three images for real-time generation; the model accepts up to nine when real-time speed is not required. Up to three audio references can guide voices and soundtracks. Generate a clip, then play it when it is ready. You can queue more clips and choose their playback order, or enable autoplay to play ready clips as they arrive.

At a glance

Spec	Value
Model name	`reactor/fast-h3-omni`
Pricing
Input	Text, image and audio references, first and last frame keyframes, and clip continuation
Output tracks	`main_video` and `main_audio`
Clip length	About 5–15 seconds
Frame rate	24 frames per second
Aspect ratios	16:9 (1344 × 768), 1:1 (768 × 768), 9:16 (768 × 1344), and 4:3 (1024 × 768)

Key features

Video with sound

Describe the scene, camera, dialogue, and soundscape in one prompt.

References

Use reference images for characters and settings, keyframe images for the opening or closing frame, and audio clips for a voice or soundtrack.

Clip control

Queue clips, choose playback order, and continue a generated scene.

Quick start

npm
pnpm

npx create-reactor-app my-omni-app --model=fast-h3-omni

pnpm create reactor-app my-omni-app --model=fast-h3-omni

Create a server-issued session token for the model, then connect with the base JavaScript SDK. The browser must not contain your rk_ API key. See Authentication for token creation.

import { Reactor } from "@reactor-team/js-sdk";

const reactor = new Reactor({ modelName: "reactor/fast-h3-omni" });
const video = document.querySelector("video")!;
const audio = document.querySelector("audio")!;

reactor.on("trackReceived", (name, _track, stream) => {
  if (name === "main_video") {
    video.srcObject = stream;
    void video.play().catch(console.error);
  }
  if (name === "main_audio") {
    audio.srcObject = stream;
    void audio.play().catch(console.error);
  }
});

reactor.on("statusChanged", async (status) => {
  if (status !== "ready") return;
  await reactor.sendCommand("enqueue", {
    prompt: "A ceramic artist turns a blue bowl under warm studio light. The camera slowly pushes in. A pottery wheel hums and rain taps the window.",
    seconds: 5.875,
  });
});

reactor.on("message", async (message) => {
  if (message.type === "clip_generated") {
    await reactor.sendCommand("play", { clip_id: message.data.clip.clip_id });
  }
});

await reactor.connect(await getToken()); // Implement getToken() on your server.

Start this example from a user action if the browser blocks audio autoplay. The typed SDK package @reactor-models/fast-h3-omni adds named methods and hooks. See Typed Model SDKs.

How it works

Connect to reactor/fast-h3-omni.
Optionally upload image or audio references and keyframe images, then call enqueue with a text prompt.
Wait for clip_generated, then call play to stream the clip, or enable autoplay.
Queue more clips, change their playback order, or continue an earlier generated clip.

A keyframe needs at least one ordinary reference image in the same request. To continue from a generated clip, the default latent mode carries motion, camera, and sound; frame mode uses the previous clip’s final frame as the next clip’s first frame. See the schema. The prompt guide and tutorial show how to build a complete clip.

Overview

FastH3-Omni

Vidu S2-Avatar

Vidu S2-Editing

H3 Reference Turbo Realtime

FastH3

Visko Orbis Stable

Visko Orbis Dynamic

HappyOyster

LingBot World 2

LingBot

X2

Helios

LongLive-2.0

SANA-Streaming

LTX

FastH3-Omni overview

At a glance

Key features

Video with sound

References

Clip control

Quick start

How it works

​At a glance

​Key features

Video with sound

References

Clip control

​Quick start

​How it works

At a glance

Key features

Quick start

How it works