Meta

Muse Video

MetaPer Request
Alias:muse-video
Create API Key

Compare muse-video API pricing, supported endpoints, capabilities and access options on Modelsell.

MetaMuse文生视频原生音频异步任务
Starting price
Per Request
Context
—
Maximum input window
Modalities
→
Released
Jul 2026

Pricing by Supplier

Meta
-20%
Meta Muse 多模态模型
Price/ request
$0.08$0.1

Capabilities / Supported modalities

Function callingToolsJSON modeStructured output
Input
Output

Provider & data privacy

Provider
Unknown
Tokenizer
BPE (vendor-specific)
License
Provider-specificUnknown
Data retention59 daysNot used for upstream training by default

Performance

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis 2026-09-30·Muse Video

This model is not included in the current benchmark snapshot.

Missing models or measurements are not zero scores.

Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.

About Muse Video

Muse Video

Muse Video 是 Meta Superintelligence Labs 开发的 Muse 系列视频生成模型,与 Muse Image 共享预训练基础,支持从文字描述生成带原生音频的视频。适合商品展示、社交内容、场景概念和短片创意验证。

模型特点

  • 可以在提示词中一并描述主体、动作、场景、运镜,以及环境声、音效、对白或背景音乐。
  • Meta 官方介绍强调提示词遵循、画面质量与时序一致性,并说明音画同步、快速运动的物理准确性仍有改进空间。
  • 发布日期记为 2026 年 7 月 7 日,指官方首次预览日期。参数量、上下文长度和知识截止日期未公开,不作推测。

ModelSell 接入

本站模型 ID 为 muse-video,通过已接入的第三方渠道提供异步视频任务。创建后轮询任务状态,完成后下载视频。本站接口与 Meta 官方接口应分别理解,实际参数及可用性以所选渠道为准。

当前渠道已有文生视频成功记录:duration: 2、size: "16:9",返回 1280×720、2 秒的 MP4,并包含视频与音频轨道。这是一次已验证的调用结果,不代表模型只支持 2 秒,也不据此承诺其他时长、分辨率、参考图或首尾帧能力。

创作建议

每个短片先聚焦一个清楚的事件:交代主体和动作,再补充镜头、光线与声音。需要对白时直接写出内容;复杂动作、精细文字与口型应检查完整成片。提示词中的声音描述是创作意图,生成结果仍需试听和检查。

资料核实日期:2026-11-09。Meta 官方介绍

Use cases and prompting

调用方式

使用 API Key 的 Bearer 鉴权。当前生产接入已验证以下 JSON 请求:

POST /v1/videos
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
{
  "model": "muse-video",
  "prompt": "A small red ball slowly rolling across a clean white tabletop, fixed camera, soft studio lighting, no text.",
  "duration": 2,
  "size": "16:9"
}

duration 使用整数秒。上述请求已成功返回 2 秒、720p、带音频轨道的 MP4。当前网关将 seconds 定义为字符串,数字形式的 seconds: 2 会被拒绝;建议先使用上述已验证的 duration 写法。

创建接口返回任务 id 后,使用 GET /v1/videos/{task_id} 查询状态。每 3–5 秒查询一次;等待 status 为 completed,若为 failed 则读取错误原因。完成后使用 GET /v1/videos/{task_id}/content 下载视频,查询与下载同样携带 Bearer 鉴权。

提示词示例

一杯冰柠檬汽水放在干净的浅色桌面,气泡缓缓上升,镜头固定,柔和自然侧光。只保留杯子与少量柠檬片,不出现文字。声音为轻微气泡声与安静的室内环境声。

先检查主体是否稳定、动作是否连贯,再调整运镜、光线和声音。建议一次只改变一个创作要求。

参数范围

本页示例针对当前已接入渠道。其他时长、比例、分辨率及参考图参数尚未在此渠道确认,请勿直接套用其他服务商的 muse-video 文档。费用以本站当前分组报价为准。

API access

API documentation

Code samples

Create taskPOST/v1/videos
Example request
Parameters
ParameterTypeDefault / rangeDescription
promptrequired
string—Text description of the desired video
size
enum
=720p
Output video resolution
seconds
integer
=4>= 1
Video length in seconds
images
array—Reference images for image-to-video generation
metadata
object—Provider-specific video generation options
Query taskGET/v1/videos/{task_id}
Example request
Parameters
ParameterTypeDefault / rangeDescription
task_idrequired
string—Task identifier returned by the generation request

Replace <YOUR_API_KEY> with the API key from your token settings.

Authentication

All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.

Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.

Rate limits

SupplierRPMTPMRPD
MetaUnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about muse-video

What is muse-video?

Compare muse-video API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call muse-video?

Create an API key with access to muse-video, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.

How is muse-video priced?

Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.

How should I evaluate muse-video for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.