wan-video/wan-2.7-t2v

Generate videos with audio from text prompts using Alibaba's Wan 2.7 model. 1080p, up to 15 seconds, with audio synchronization.

Capabilities

Negative PromptSeed

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`prompt`*	string	Text prompt for video generation	`—`	—
`aspect_ratio`	string	Aspect ratio of the generated video	`"16:9"`	16:99:161:14:33:4
`audio`	string(uri)	Audio file (wav/mp3, 3-30s, ≤15MB) for voice/music synchronization. If not provided, the model auto-generates matching audio.	`—`	—
`duration`	integer	Duration of the generated video in seconds	`5`	min: 2, max: 15
`enable_prompt_expansion`	boolean	Automatically expand and optimize the prompt for better results. Improves quality for short prompts but increases latency.	`true`	—
`negative_prompt`	string	Negative prompt — describes content that should not appear in the video	`""`	—
`resolution`	string	Output video resolution	`"1080p"`	720p1080p
`seed`	integer	Random seed for reproducible generation. Range: 0-2147483647	`—`	—

promptrequiredstring

Text prompt for video generation

aspect_ratiostring

Aspect ratio of the generated video

Default: "16:9"

16:99:161:14:33:4

audiostring

Audio file (wav/mp3, 3-30s, ≤15MB) for voice/music synchronization. If not provided, the model auto-generates matching audio.

durationinteger

Duration of the generated video in seconds

Default: 5min: 2, max: 15

enable_prompt_expansionboolean

Automatically expand and optimize the prompt for better results. Improves quality for short prompts but increases latency.

Default: true

negative_promptstring

Negative prompt — describes content that should not appear in the video

Default: ""

resolutionstring

Output video resolution

Default: "1080p"

720p1080p

seedinteger

Random seed for reproducible generation. Range: 0-2147483647

Version: 6c53841e185bUpdated: 8/1/20269.2K runs