Muse Video is Meta's video model. Meta previewed it on July 7, 2026 together with Muse Image, but has not put it on its own API - in Jantaris you call it with your regular key. It is simple to use: it always returns one clip of about 10 seconds at 720p with sound. You choose only the aspect ratio (16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3) and can add up to 9 reference images. The price is flat per clip, regardless of aspect ratio or references.
You cannot set length or resolution. For a shorter shot, 1080p or a frame pair, PixVerse V6 Max or Gemini Omni 1.2 fit better.
Best for
- Many variants of one scene on a small budget
- 9:16 reels and 3:4 social frames
- Quick motion drafts before a pricier model
- Character or product scenes from reference images
How to write prompts
- Write one scene per 10 seconds: what happens, camera movement, sound.
- Add the sound at the end (splash, bark, crowd) - audio is on by default.
- Add "no text" if letters show up in the frame.
FAQ
How much does Muse Video cost?
$0.0528 per video. Failed generations are not charged.
How long is a clip?
About 10 seconds, always 720p. These values cannot be changed.
Can I turn off the sound?
Yes, with the "Generate audio" switch. The price stays the same.
How to call Muse Video via API
curl https://jantaris.com/v1/generate?wait=60 \
-H "Authorization: Bearer $JANTARIS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "muse-video",
"input": {
"prompt": "A slow dolly shot through a neon-lit night market in the rain, reflections on wet asphalt, cinematic",
"aspect_ratio": "16:9"
}
}'import os, time, requests
API = "https://jantaris.com/v1"
H = {"Authorization": f"Bearer {os.environ['JANTARIS_API_KEY']}"}
task = requests.post(f"{API}/generate", headers=H, json={
"model": "muse-video",
"input": {
"prompt": "A slow dolly shot through a neon-lit night market in the rain, reflections on wet asphalt, cinematic",
"aspect_ratio": "16:9"
}
}).json()
while task["status"] in ("queued", "running"):
time.sleep(3)
task = requests.get(f"{API}/tasks/{task['id']}", headers=H).json()
print(task["status"], task["cost"], [o["url"] for o in task["output"]])const API = "https://jantaris.com/v1";
const headers = { Authorization: `Bearer ${process.env.JANTARIS_API_KEY}`, "Content-Type": "application/json" };
let task = await (await fetch(`${API}/generate`, {
method: "POST",
headers,
body: JSON.stringify({
"model": "muse-video",
"input": {
"prompt": "A slow dolly shot through a neon-lit night market in the rain, reflections on wet asphalt, cinematic",
"aspect_ratio": "16:9"
}
}),
})).json();
while (task.status === "queued" || task.status === "running") {
await new Promise((r) => setTimeout(r, 3000));
task = await (await fetch(`${API}/tasks/${task.id}`, { headers })).json();
}
console.log(task.status, task.cost, task.output.map((o) => o.url));Parameters
| Parameter | Type | Allowed | Default |
|---|---|---|---|
prompt * | string | ||
aspect_ratio | string | 16:9 9:16 1:1 4:3 3:4 3:2 2:3 | 16:9 |
generate_audio | boolean | true | |
image_urls | array | max 9 |
The same schema is available from GET /v1/models/muse-video.