Is There a Meta Muse Video API? Official API, Free Tools and a Hosted API (2026)
6 min read • October 18, 2026 (October 30, 2026)
Table of contents
- Does Meta Muse have a video API?
- Compared
- Why useapi.net for Meta Muse video
- How to start
- Frequently asked questions
- Sources
Does Meta Muse have a video API?
Meta has no Muse video API (as of October 30, 2026): its official Model API sells the Muse Image model, the Muse Wonder and Muse Spark text models, Muse Voice Transcribe for speech to text and SAM 3.1 for segmentation, and none of them outputs video. The 10-second videos with sound that Muse makes at muse.ai are reached through third-party tools that drive the Muse agent on your Muse website subscription, such as the hosted useapi.net Muse API.
There are three kinds of options:
- Meta’s Model API, if you need Muse images or the Muse text models. It sells Muse Image at $0.01 per image, and Muse Wonder (launched on October 12, 2026) at $4 per million input tokens and $20 per million output tokens (Meta pricing, TechCrunch).
- Free self-hosted tools, such as muse2api, an open-source server that wraps muse.ai in OpenAI-compatible endpoints, and local MCP bridges such as Muse-Chat-MCP, which drives your logged-in Chrome. You run them on your own machine or server.
- Hosted APIs: per-request resellers such as museai.suncodevn.com, which sell credit packs, and the useapi.net Muse API, which runs on your Muse website subscription with no per-video charge, over REST and as a hosted MCP server.
This page is written by the useapi.net maintainers and compares what each option offers from its own documentation.
Compared
| useapi.net | Meta Model API | muse2api | Per-request resellers | |
|---|---|---|---|---|
| Muse video generation | ||||
| Chat with the Muse agent at muse.ai | ||||
| Hosted, nothing to install or run | ||||
| Sign in with email and password, no cookies to copy, session renewed for you | API key | |||
| No per-video charge | no video | |||
| Hosted MCP server for Claude Code, Cursor, VS Code | not in its docs | not in its docs | not in its docs | |
| Price | Your Muse website subscription the free plan made about 30 to 50 videos a week | $0.01 per image, text models per token | Free, you host it | 6 credits a video, packs from $3.90 for 500 credits |
From each option’s own documentation and pricing on October 30, 2026: Meta models and pricing, muse2api v1.6.4, and museai.suncodevn.com’s published plans as the per-request example (on your Meta account it charges 4 credits a video on its Developer and Pro plans). useapi.net is a third-party API and is not affiliated with Meta.
Why useapi.net for Meta Muse video
- POST /jobs/video makes a video of about 10 seconds at about 720p, with sound, from text, a photo or another video. Lines written in quotes are spoken, so a single photo becomes a talking photo, and a person in a clip can be swapped for someone from a photo.
- POST /chats talks to the whole Muse agent at muse.ai, with its answers streamed live over Server-Sent Events, and you can watch and take over its web browser.
- The hosted MCP server has 37 tools and adds to Claude Code, Cursor or VS Code with one line. It is listed in the official MCP Registry as
net.useapi/muse, and there is nothing to install. - There is nothing to run on your machine, with no server to deploy, no browser to keep open and no extension to install. Jobs keep running when your laptop is off.
- You add the account once with its email and password, and we keep it signed in and renew its 30-day Muse session, with no cookies to copy or refresh.
- It runs on your Muse website subscription, and the free plan works. Each video uses about 2 to 3 percent of the free plan’s weekly allowance in our tests.
- Each subscription adds 3 Muse accounts, and a job without an
emailgoes to a healthy account with allowance left and a free slot. - A job can wait for the finished file, or you send
async: trueand the job record is posted to yourreplyUrl. - A ready-made n8n template and an agent skill get you started, with no per-image or per-video charge from us.
A Muse video made through the useapi.net API: the rider from a photo swapped into a clip Muse made from a still image. Every request is in the tutorial.
How to start
What the Muse account needs:
- Muse is available in the US, Canada, Japan and Singapore (as of October 30, 2026), so create the account in one of them. Once it is added, you can call the API from anywhere.
- Finish Muse’s onboarding at muse.ai, including Meta’s age check, and create one image there.
- The account must have email + password sign-in, because the API signs in with the email and password. A Meta account that signs in only with an emailed code has no password yet: create one in Meta Accounts Center (Password and security), then add the account here. Without a password the add is refused with
400. - Use the account only for the API, with no other automation tools on it. Opening it at muse.ai in a browser is fine, but only from the US, Canada, Japan or Singapore (the regions Muse officially supports), or through a VPN in one of them: Meta can switch off video for an account it sees used from elsewhere.
Then:
- Get a useapi.net API token.
- Add your Muse account once with Setup Muse. The free Muse plan works.
- Make a 10-second video with sound in one call:
curl -X POST https://api.useapi.net/v1/muse/jobs/video \
-H "Authorization: Bearer $USEAPI_TOKEN" \
-H "Content-Type: application/json" \
-d '{"prompt": "A golden retriever runs along a beach at sunset while the camera tracks beside it. A man off screen calls: \"Good boy, come here!\" In exactly 16:9 aspect ratio."}'
The request waits for the video, which took 60 to 140 seconds in our tests, and answers with the job record. The video is the first assetId in result.assets[]: download it with GET /assets/assetId. A slower job answers 202, and you fetch it with GET /jobs/jobid.
Or add the MCP server to Claude Code with one line:
claude mcp add --transport http useapi-muse https://api.useapi.net/v1/muse/mcp --header "Authorization: Bearer YOUR_API_TOKEN"
Step-by-step tutorial: How to Generate AI Videos and Images with the Meta Muse API (talking photos, image to video, person swap, photo restoration). Runnable code: useapi/muse-api.
Start using the API
A single $15/month subscription covers every API on useapi.net — one token, all services. You connect up to 3 accounts per service, each with its own website subscription, and useapi.net handles the REST API, load balancing, and polling. Need more accounts? Each extra subscription is $10/month and adds 3 more accounts per service.
Subscribe — $15/month Pay with crypto
Pricing and volume options — full refund within the first 14 days if you have fewer than 50 successful generations. Already subscribed? Change the quantity in the Stripe Customer Portal instead of buying again.
Frequently asked questions
Is there a Muse API? Through useapi.net, yes: POST /jobs/video makes an MP4 of about 10 seconds at about 720p with sound, from a prompt, up to 9 images, 3 videos or 3 audio files, and a line written in quotes is spoken. Meta’s official Model API sells the Muse Image model at $0.01 per image, but as of October 2026 it has no video generation and no API for the Muse agent at muse.ai, where the videos are made.
Is there a Meta Muse API key? Through useapi.net, no Meta key is needed: one useapi.net API token calls the Muse API, and you add your Muse account once with its email and password at Setup Muse. Create that account in the US, Canada, Japan or Singapore, where Muse is available (as of October 2026), and after that you can call the API from anywhere.
What is a good muse2api alternative? Through useapi.net, the Muse API is hosted, so there is nothing to run: no Docker, no browser extension and no cookies to push, and we keep the account signed in and renew its session. It has image and video jobs with webhooks, streamed chat with the agent, and a hosted MCP server with 37 tools.
Is there a free Muse API? Through useapi.net, the Muse API works on the free Muse plan, where one account made roughly 30 to 50 videos a week in our tests. Once one account’s allowance is used up, new jobs go to your other accounts, and the paid Power ($20 a month) and Maximum ($100 a month) plans raise it (as of October 2026).
Where do my Muse videos and images go? Through useapi.net, Muse runs on your Muse website subscription, so every image and video it makes also sits in that account’s Library at muse.ai. The Library endpoints list and download them, and you can pass any of them into a new job by its asset id.
Sources
Checked on October 30, 2026:
- Meta Model API: models (inputs and outputs of each model) and pricing (Muse Image $0.01 per image, Muse Wonder $4 / $20 and Muse Spark 1.1 to 1.3 $1.25 / $4.25 per million input / output tokens, Muse Voice Transcribe $0.18 per hour of audio, SAM 3.1 per image and video frame, no video generation model)
- TechCrunch, October 12, 2026: Meta releases Muse Wonder
- czg86389-hub/muse2api README, v1.6.4 (October 27, 2026): OpenAI-compatible chat, image and video endpoints, Docker Compose deployment, session cookies sent by a Chrome extension or a Tampermonkey script, MIT license
- duclm1x1/Muse-Chat-MCP README: a local MCP server that drives Chrome with Playwright
- museai.suncodevn.com plans and request costs: chat 1, image 3 and video 6 credits, 20 free credits, 500 credits for $3.90, 1,000 for $15.70, 6,000 for $58.60
- useapi.net: the Muse API reference, POST /jobs/video, POST /accounts and the MCP server