Tasks and inputs
Muse Video is listed for Text-to-video. It accepts text and produces video, audio. Use the publisher’s input format and preprocessing for your chosen deployment.
Muse Video is Meta’s previewed video-generation model with native audio; a public Meta Model API route and price have not been established.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Meta previewed Muse Video alongside Muse Image on 7 July 2026. The video model builds on the same pretraining base and supports native audio generation. The announcement describes it as an early preview, with further work on audio-video synchronization and difficult motion. This profile keeps that preview status separate from an established developer API release.
The preview announcement discusses creator and Meta AI experiences. The current Meta Model API catalog lists the image, text, transcription and segmentation interfaces but does not establish a Muse Video route. This profile therefore leaves the API identifier and price empty. An endpoint name must not be invented from the product’s display name.
If the product is available on your account, retain the prompt, duration and output settings with each clip. Inspect temporal consistency, motion and whether generated audio matches the visible action. Count accepted clips and the revisions needed to reach them. Do not reuse Muse Image’s per-image price to estimate video cost.
Use short scenarios with a clear subject, action and timing requirement. Include dialogue or a sound tied to a visible event when evaluating native audio. Watch the whole clip rather than one frame, and compare synchronization and motion continuity separately from visual sharpness.
Record the exact model identifier, deployment route and request settings with each result. Count complete runs, including rejected outputs, retries and tool calls. When the workflow creates files or code, open the files or execute the existing checks before accepting the result. A plausible first response can hide an incomplete final deliverable.
The specifications describe supported interfaces and request capacity. They do not establish a measured quality ranking or a latency guarantee for your account. SyncDev has not independently benchmarked this model. Choose a deployment after testing the languages, input formats and operating conditions that matter to your users.
Explore meta models, browse model tasks, or compare two models with the same acceptance criteria.
Compare the model on the work you need to complete.
Muse Video is listed for Text-to-video. It accepts text and produces video, audio. Use the publisher’s input format and preprocessing for your chosen deployment.
Choose duration, resolution and frame rate together. Compare the cost of an accepted clip, including repeat generations.
Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Wan-AI
Hugging Face repository for Text-to-video.
AaronHuangWei
Hugging Face repository for Text-to-video.
Abiray
Abiray/LTX-2.3-22B-DISTILLED-1.1-GGUF is a source-linked Hugging Face repository assigned to Text-to-video. Its recorded task interface accepts text and produces video.
Abiray
Abiray/Sulphur-2-base-GGUF is a source-linked Hugging Face repository assigned to Text-to-video. Its recorded task interface accepts text and produces video.
aidealab
Hugging Face repository for Text-to-video.
alibaba-pai
Hugging Face repository for Text-to-video.