Picture and sound together
Describe the sounds, music or lines in the prompt and they come with the picture in one pass.
The Muse Video API: Meta's text-to-video model makes 720p clips with native sound from a prompt, from $0.02 per second.
muse-videoUpdated import os, time, requestsAPI = "https://api.zurelay.com/v1"KEY = os.environ["ZURELAY_API_KEY"]headers = {"Authorization": f"Bearer {KEY}"}res = requests.post(f"{API}/videos", headers=headers, json={ "model": "muse-video", "prompt": "A red fox trotting through snow at dawn, cinematic", "seconds": 5, "resolution": "720p", "aspect_ratio": "16:9",})res.raise_for_status()job = res.json()url = f"{API}/videos/{job['id']}"# Takes a few minutes: poll until it's donewhile job["status"] in ("queued", "in_progress"): time.sleep(5) job = requests.get(url, headers=headers).json()if job["status"] == "failed": raise SystemExit(job["error"]["message"])video = requests.get(f"{url}/content", headers=headers)with open("video.mp4", "wb") as f: f.write(video.content)print(f"Saved video.mp4 for ${job['cost']}")Base URL https://api.zurelay.com/v1. Plain JSON over HTTPS: start a job, poll it, download the MP4. Muse Video guide
Pricing
Pay as you go from prepaid credit, with no subscription. Top up from $10. A video is charged only once it's delivered; videos that fail cost nothing.
A clip costs its length in seconds times the price at its resolution. It's held from your balance when the job is accepted and charged when the video is delivered. The aspect ratio don't change the price.
Every AI video model and pricePick a resolution and a length, and how many videos you make.
100 clips × $0.10
Cost
Typical workloads at Zurelay's live prices, next to the list price.
5 s at 720p.
10 s at 720p, the longest and sharpest it makes.
100 clips of 5 s at 720p.
Overview
Muse Video is Meta Superintelligence Labs' video generation model, which makes video and its sound together from a text prompt. On Zurelay it makes 720p clips of 5 to 10 seconds in 16:9 or 9:16, with the ambience, effects, music or dialogue your prompt describes. The Zurelay Muse Video API costs $0.02 per second, and a video is charged only once it's delivered.
Muse Video is a video generation model from Meta Superintelligence Labs, which Meta introduced on July 7, 2026, together with Muse Image, as an early preview. Meta says it does well on following the prompt, picture quality and keeping things consistent over time, and that it's still improving the sync between sound and picture and the physics of fast motion. On Zurelay it uses the model ID muse-video, and also accepts meta/muse-video.
On Zurelay, Muse Video makes video from text only: describe the subject, the action, the setting and the camera, and the sound you want, such as ambient noise, effects, dialogue or music. It doesn't take a start image or reference images. Clips are 720p, 1280 × 720 in 16:9 or 720 × 1280 in 9:16, in whole seconds from 5 to 10, and always come with sound.
Video takes time, so the API is asynchronous. POST https://api.zurelay.com/v1/videos returns a job right away; poll GET /v1/videos/{id} until its status is completed, then download the MP4 from /v1/videos/{id}/content or from the signed url in the job. A clip usually takes about 2 minutes. Videos are kept for 30 days.
Zurelay prices Muse Video by the second: $0.02 per second, so a 5 second clip costs $0.10. Sound is always included at no extra cost. The price is held from your balance when the job is accepted and charged only when the video is delivered. Videos that fail, including ones the content filter refuses, cost nothing. Meta hasn't published an API price for Muse Video.
Strengths
Describe the sounds, music or lines in the prompt and they come with the picture in one pass.
Meta built Muse Video for prompt adherence, picture quality and consistency from frame to frame.
$0.02 per second at 720p with sound included, so a 10 second clip costs twice a 5 second one and no more.
1280 × 720 for 16:9 or 720 × 1280 for 9:16, ready for the web or for short-form social video.
Use cases
Vertical 9:16 clips with sound for reels and shorts, straight from a prompt.
Try a setting, a mood or a camera move before you shoot or render anything bigger.
Nature, city and studio shots with their own ambient sound, to fill an edit.
Make several takes of the same idea and keep the best one.
Get started
No waitlist and nothing to install: three HTTPS endpoints and your API key.
Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.
Every video endpoint lives under this base URL. Send your key as a Bearer token.
https://api.zurelay.com/v1POST a prompt to /v1/videos, poll the job every few seconds until it's completed, then download the MP4. Videos are kept for 30 days.
muse-videoWorks with the tools you already use
Compare
from $0.025 per second
Pick Veo 3.1 Fast for Google's 8 second clips with dialogue, from a prompt or a start image.
Veo 3.1 Fast APIfrom $0.071 per second
Pick Grok Imagine Video 1.5 for clips with sound from a start image or up to 3 reference images.
Grok Imagine Video 1.5 APIfrom $0.039 per second
Pick Wan 3.0 for first and last frames, up to 10 reference images and clips of up to 30 seconds.
Wan 3.0 APIZurelay charges $0.02 per second of video, so a 5 second clip is $0.10 and a 10 second clip twice that. Sound is always included. The price is held from your balance when the job is accepted and charged only when the video is delivered; videos that fail cost nothing.
Not publicly. Meta introduced Muse Video on July 7, 2026, and as of November 2026 its Model API offers Muse Image but not Muse Video, with no published price. Zurelay gives you API access to Muse Video through the same /v1/videos endpoint as its other video models. Zurelay is an independent service and is not affiliated with Meta.
Send POST https://api.zurelay.com/v1/videos with your Zurelay key as a Bearer token and a JSON body: model set to muse-video, a prompt, and optionally seconds (5 to 10, default 5) and aspect_ratio (16:9 or 9:16). You get a job back right away. Poll GET /v1/videos/{id} every few seconds until its status is completed, then download the MP4 from /v1/videos/{id}/content.
No. Muse Video on Zurelay makes video from text only, and a request with a first_frame or reference_images is refused before anything is charged. To start from an image, use a model such as Wan 3.0, Kling 4.0 or Veo 3.1 Fast.
Yes, every clip comes with sound generated with the picture. Describe what you want to hear in the prompt: ambient noise, sound effects, music or spoken lines in quotes. Meta notes that sync between sound and picture is still improving, so check lip sync on dialogue.
720p only: 1280 × 720 for 16:9 or 720 × 1280 for 9:16, in whole seconds from 5 to 10.
Usually about 2 minutes; in our tests clips took one to three minutes. While you poll, the job's progress field gives an estimate from 0 to 100.
Create a key in seconds, point the SDK you already use at Zurelay, and every request costs up to 90% less from the first token.