LTX-2 Retake performs targeted retakes on any section of a video—replace visuals, audio, or both—while preserving timing and continuity with $0.1 per output video second. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Inattivo
$0.1per esecuzione·~10 / $1
EsempiVedi tutto
Change the time in the video from daytime to nighttime.
From 2s to 8s. Make the robot, saying in English: 'Master, the people outside are dangerous.' Keep the background, lighting, and camera angle the same, with natural robotic lip-sync and a worried tone.
Remove the man on the left.
Replace the man in the video with a woman.
Change the woman's clothes in the video to red. Do not alter the camera, composition, background, lighting, faces, or any other details.
Modelli correlati
README
lightricks/ltx-2-retake 🎬
LTX-2 Retake is Lightricks’ next-generation AI video refinement model for “reshooting” part of a finished clip—without bringing the crew back or regenerating the whole video.
Instead of rebuilding the scene from scratch, Retake lets you describe what should change in natural language while it preserves the rest of the footage, keeping lighting, motion continuity, composition, and environment consistent.
🔧 What it can do
- 🎬 Retake a moment in an existing shot – describe which part of the clip should change (for example, “between 3s–7s, make it nighttime”) and Retake focuses edits on that region while keeping the rest stable.
- 🎤 Rewrite or replace dialogue while preserving the speaker’s identity and general performance style.
- 🎥 Adjust performance – refine expressions, gestures, pacing, or emotional delivery.
- 📷 Tweak camera feel – subtly change framing, zoom, or camera motion style.
- 🎧 Refresh the audio track – update voiceover, ambience, or background music, depending on the selected mode.
- 🔄 Blend seamlessly – uses the original video as context so transitions in and out of the edited part remain smooth.
✨ Why Retake?
Because high-quality revision shouldn’t require starting from scratch. LTX-2 Retake gives you surgical control over moments inside an existing video—fast, flexible, and production-ready.
📦 Input parameters
| Parameter | Description |
|---|---|
| prompt* | Natural-language instructions for the retake: what to change, how it should look or sound, and (optionally) which time span in the clip you want to modify. |
| video* | Original clip to refine. |
| mode | Editing mode: replace_video (change visuals, keep audio), replace_audio (keep visuals, regenerate audio), or replace_audio_and_video (update both picture and sound). |
Output resolution is currently fixed at 1080p in this integration.
👉 Time ranges: If you need to target a specific segment, write the time window directly into the prompt, for example: “From 00:05 to 00:10, change the time of day from afternoon to nighttime while keeping the same actor and camera angle.”
💰 Pricing
| Actual clip duration | Billed seconds | Effective rate per second | Total price |
|---|---|---|---|
| ≤ 2 s | 2 s | $0.10 / s | $0.20 |
| 5 s | 5 s | $0.10 / s | $0.50 |
| 10 s | 10 s | $0.10 / s | $1.00 |
| ≥ 16 s | 16 s (capped) | $0.10 / s | $1.60 |
Billing Rules
- Minimum billed duration: 2 seconds
- Maximum billed duration: 16 seconds (anything longer is still charged as 16s)
🎯 When to use LTX-2 Retake
- Creating alternative takes without new shoots
- Iterating on performance, tone, or pacing after feedback
- Producing multiple ad or promo versions from a single master edit
- Fixing specific dialogue lines while keeping everything else
- Updating VO, ambience, or music while preserving visuals
- Nudging lighting, time-of-day, or camera feel to better match the story
📌 Practical notes
- Works best when the original clip has stable lighting and camera work around the area you are retaking.
- Render time depends on clip duration and the complexity of the requested changes.
- For precise control, mention in the prompt both what must change and what must stay the same (for example, “keep the same actor, outfit, and framing, but make the scene at night and soften the expression”).
More Video Edit Tools on WaveSpeedAI
- video-head-swap – replaces the entire head (face + hair + outline) of a person in video using a reference image, while keeping the original body, motion, and background.
- video-eraser – removes unwanted objects, people, or watermarks from video with temporal-aware inpainting that keeps motion and background consistent.
- video-face-swap – swaps only the facial identity in a clip, preserving expressions, lighting, and head pose for natural-looking replacements.
- video-upscaler-pro - Upscale videos to 720p, 1080p, 2K, or 4K with a simple upload. This is the most advanced video upscaler in the world, delivering the highest output quality and exceptional frame-to-frame consistency.
Ltx 2 Retake API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/lightricks/ltx-2-retake with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Ltx 2 Retake below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/lightricks/ltx-2-retake" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://example.com/your-input.mp4",
"mode": "replace_audio_and_video"
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("lightricks/ltx-2-retake", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://example.com/your-input.mp4",
"mode": "replace_audio_and_video"
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"lightricks/ltx-2-retake",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://example.com/your-input.mp4",
"mode": "replace_audio_and_video"
}
)
print(output["outputs"][0]) # → URL of the generated outputLtx 2 Retake API — Frequently asked questions
What is the Ltx 2 Retake API?
Ltx 2 Retake is a Lightricks model for video editing, exposed as a REST API on WaveSpeedAI. LTX-2 Retake performs targeted retakes on any section of a video—replace visuals, audio, or both—while preserving timing and continuity with $0.1 per output video second. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Ltx 2 Retake API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/lightricks/lightricks-ltx-2-retake.
How much does Ltx 2 Retake cost per run?
Ltx 2 Retake starts at $0.10 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Ltx 2 Retake accept?
Key inputs: `prompt`, `video`, `mode`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/lightricks/lightricks-ltx-2-retake.
How long does Ltx 2 Retake take to generate?
Average end-to-end generation time on WaveSpeedAI is around 44 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Ltx 2 Retake outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (Lightricks). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.