LongCat Avatar 1.6
longcat-avatar-1.6Animate one person or two people from an image and speech or singing audio. Supports lip-synced talking and singing, optional expression prompts, simultaneous or sequential two-person dialogue, and 480p or 720p output. Clips are limited to 64 seconds; longer audio is trimmed.
Pricing
Includes our margin. Charged per request from your balance.
Per second by resolution
- 480p
- $0.044
- 720p
- $0.088
- Default resolution
- 480p
- Maximum billable duration
- 64 s
- Minimum billable duration
- 3 s
Billing: Each measured audio track is rounded up to whole seconds. Single: audio length. Two people: longer rounded track for meanwhile; sum of rounded tracks for sequential order. Minimum 3 and maximum 64 billable seconds. Longer audio is trimmed. One output; prompt and seed have no extra charge.
Details
- Provider
- LongCat
- Added
- Nov 17, 2026
Options
Parameters this model accepts.
| Parameter | Values | Default |
|---|---|---|
seed-1 chooses a random seed. | Number Default | -1 |
audioRequired in single mode. Audio is measured from pinned input bytes before billing. | Text | — |
order | Together, Left then right, Right then left Default | meanwhile |
imageUrlOne image showing the person or both people. An authorized image attachment may be used instead. | Text | — |
left_audioRequired in multi mode: audio for the person on the left. leftAudioAttachmentId is also accepted. | Text | — |
resolution | 480p, 720p Default | 480p |
right_audioRequired in multi mode: audio for the person on the right. rightAudioAttachmentId is also accepted. | Text | — |
generation_mode | One person, Two people Default | single |