When was Muse Video released?

Meta previewed Muse Video on July 7, 2026, and said it was coming soon to creators and Meta AI. Muse Video is callable on reAPI now under the model id muse-video.

Can I call Muse Video through an API?

Yes, on reAPI. As of October 29, 2026, Muse Video is not in Meta's own Model API model list. On reAPI you POST to /api/v1/videos/generations with model muse-video and poll the task for the finished clip.

Is Muse Video free or paid?

Calling Muse Video on reAPI is paid: each clip costs one flat price at $1 = 1,000 credits, and failed tasks are refunded automatically. See the pricing table on this page for the current rate.

Does Muse Video require a monthly subscription?

No. reAPI is pay as you go: you buy credits, each Muse Video task deducts its price, and unused credits never expire. There is no monthly plan to keep.

How do I get a Muse Video API key?

Sign up at reAPI and create a key under Settings, API keys. The same key works for Muse Video and every other model on reAPI; send it as a Bearer token.

How much does Muse Video cost?

Muse Video has one price per clip, and it is not multiplied by seconds. Text-only and reference requests cost the same, and so does every aspect ratio. The current rate is in the pricing table on this page.

How long are Muse Video clips?

About 10 seconds. Duration accepts only 10, and each request returns one clip, so longer pieces are made by joining several Muse Video clips.

Does Muse Video generate audio?

Yes, always. Sound is generated with the picture in every Muse Video clip, and audio cannot be turned off. Name the sounds you want in the prompt.

Can Muse Video turn an image into a video?

Yes. Pass the image in image_urls and describe the motion. Muse Video treats it as a reference, so the clip stays close to it but the first frame is not an exact copy. There are no first frame, last frame, video reference or extend settings.

Is Muse Video any good?

Meta reported Muse Video at No. 3 on Arena's human-preference leaderboard for text to video as of July 5, 2026. Meta also named its current gaps: audio-video synchronization and physically accurate fast motion. Test Muse Video on your own prompts before you rely on it.

Is Muse Video open source?

No. Meta has not released Muse Video weights. The open-weight models Meta lists are Muse Glimmer and Muse Spark Open, which are separate models.

Muse Video — Meta's 10-Second Video Model with Sound

Muse Video is the video model from Meta Superintelligence Labs, built on the same base as Muse Image. Write a prompt or add up to 9 reference images, and Muse Video returns a clip of about 10 seconds at 720p with sound, at one price per clip.

Highlights: About 10 s · 720p · sound in every clip
Best for: Muse Video ads, social clips and animated stills
Input: Text, plus up to 9 reference images
Output: MP4 video with audio

Input

Prompt*

Required · must not be empty

Aspect ratio

1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · default auto

Duration (seconds)

10 · default 10

Resolution

720p · default 720p

Audio

Default on

Estimated cost~$0.02424 credits

Result

Try one of these prompts

Pricing

Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.

First test cost

$0.02424 credits

One sample at the cheapest tier (1 clip).

Testing budget guide

Add credits

$10

≈ 416 tests

$50

≈ 2083 tests

$100

≈ 4166 tests

Per clip: $0.024; Price · 1 clip

What is Muse Video?

Muse Video is the video generation model from Meta Superintelligence Labs, previewed on July 7, 2026 alongside Muse Image and built on the same pretraining base. Meta describes it as delivering high visual fidelity with native audio. On reAPI, Muse Video is the model id muse-video on /api/v1/videos/generations: a prompt and up to 9 reference images in, a clip of about 10 seconds at 720p with sound out, billed at one price per clip.

Muse Video turning a prompt and a reference image into a clip with sound

What you can build with this model

Real-world workflows and production use cases you can build and ship with this model.

Muse Video animating a still image into a short clip

Set a still in motion

Make a still with Muse Image, pass its URL to Muse Video and describe the movement. The clip stays close to the picture, and with no ratio set it keeps the picture's shape.

Animate an image

A vertical 9:16 Muse Video clip with sound for social feeds

Vertical clips with sound

Set 9:16, write the scene and name the sounds. Muse Video returns a clip for Reels, Shorts or TikTok with the audio already in it, so there is no separate sound pass.

A row of Muse Video clips billed at one price each

A fixed price per clip

Every Muse Video clip costs the same, with or without references and in any ratio. A campaign of thirty clips is thirty times one price, which makes the budget easy to plan.

Why reAPI for Muse Video

One request for both jobs

Text to video and reference images share one Muse Video request on /api/v1/videos/generations. Add image_urls when you have references and leave them out when you don't.

One key for every model

The same reAPI key runs Muse Video, Muse Image, Seedance 2.0, Kling and the rest of the catalog. You don't need a separate account to use Muse Video.

Pay per clip, no subscription

Muse Video bills one price per finished clip, not per second. Credits never expire, and failed tasks are refunded automatically.

Muse Video vs Seedance 2.0

Both models run on reAPI under the same key. Muse Video gives you one fixed length and resolution at one price; Seedance 2.0 lets you set length, resolution and audio, and takes video and audio references. Pick Muse Video when a 10-second 720p clip with sound is enough.

Capability

Muse Video on reAPI

Seedance 2.0 on reAPI

Clip length

About 10 s, fixed

4 to 15 s, or auto

Resolution

720p

480p, 720p, 1080p or 4K

Audio

Always on

Optional

References

Up to 9 images

Images, video and audio

First and last frame

Not offered

Supported

Billing

One price per clip

Per second, by resolution

Values reflect each model's parameters on reAPI on October 29, 2026. Current rates are in each model's pricing table.

Call Muse Video in three steps

step 01
Create an API key
Sign up and create a key in the dashboard, then add credits for your first Muse Video clips.
Open
step 02
Try Muse Video in the playground
Write a prompt, add references if you have them, pick a ratio and generate. Copy the request from the API tab when you like the result.
Open
step 03
Send the request
POST to /api/v1/videos/generations with model muse-video, then poll the Muse Video task until it completes and download the MP4.
Open

docs/api/muse-video

API reference

Drop-in code and the full parameter table.

View full reference

curl -X POST https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "muse-video",
    "prompt": "A golden retriever shakes off water on a sunny dock, droplets flying in slow motion, the camera pushing in gently, splashes and a happy bark. No text.",
    "aspect_ratio": "16:9"
  }'

Parameter validation failed

Rejected synchronously with the failing field named. Check enum values, ranges, and URL fields — nothing is charged.

Authentication or balance issue

401 means a missing or invalid Bearer key; 402 means the reserve exceeds your balance. Manage keys and credits in the console.

Content or material rejected

Reference material and outputs pass automated moderation. Rejected tasks fail with a clear error and a full refund.

Task failed or timed out

A task that reaches a failed state is never charged — the reserve refunds automatically. Keep the task id and retry when ready.

Frequently asked questions

Common questions about this model.

Muse Video is Meta's video generation model from Meta Superintelligence Labs, built on the same pretraining base as Muse Image. It makes a clip of about 10 seconds at 720p with sound from a prompt, or from a prompt plus up to 9 reference images. On reAPI you call it as muse-video.