← All models
MMAudio generates synchronized audio given video and/or text inputs. It can be combined with video models to get videos with audio.
Example
Details
- Accepts
- video
Pricing
- Price
- 0.125 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | The seed for the random number generator |
| promptrequired | string | The prompt to generate the audio for. |
| duration | number | The duration of the audio to generate. |
| num_steps | integer | The number of steps to generate the audio for. |
| video_urlrequired | string | The URL of the video to generate the audio for. |
| cfg_strength | number | The strength of Classifier Free Guidance. |
| mask_away_clip | boolean | Whether to mask away the clip. |
| negative_prompt | string | The negative prompt to generate the audio for. |
Output
| Field | Type | Description |
|---|---|---|
| video | — | The generated video with the lip sync. |