About LTX 2.3 Retake
LTX 2.3 Retake regenerates a section of an existing clip guided by a prompt — change a line of dialogue, an action, or the sound without touching the rest. It can replace the section's video, its audio, or both.
The input video supports up to 4K and must be at least 3 seconds; output is 1080p.
Ready to build with LTX 2.3 Retake?
Try LTX 2.3 Retake in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/videos/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "ltx-2-3-retake",
"input_video": "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/videos/waterfall.mp4",
"retake_start_time": 0,
"retake_duration": 4,
"retake_mode": "replace_audio_and_video"
}'Request parameters
Every field LTX 2.3 Retake accepts in the request body. See the API reference for response formats.
POST
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
input_video | stringuri | Yes | — | The clip to retake a section of. Up to 4K, at least 3 seconds. |
prompt | string | No | — | What should happen in the retaken section. |
retake_start_time | number | No | 0 | Where the retaken section starts, in seconds. Range: 0 – +∞ |
retake_duration | number | No | 4 | Length of the retaken section in seconds, at least 2. Range: 2 – +∞ |
retake_mode | string | No | "replace_audio_and_video" | Replace the video, the audio, or both in the retaken section.replace_audio_and_videoreplace_videoreplace_audio |