Lightricks Ltx 2 Retake
Playground
Try it on WavespeedAI!LTX-2 Retake performs targeted retakes on any section of a video—replace visuals, audio, or both—while preserving timing and continuity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
lightricks/ltx-2-retake 🎬
LTX-2 Retake is a next-generation AI video refinement tool that empowers creators, editors, and studios to retake a specific segment of an existing video — without re-shooting or regenerating the full clip.
Rather than rebuilding a scene from scratch, Retake allows you to edit a localized section (2–16 seconds) while preserving the original footage around it, maintaining lighting, motion continuity, composition, and environment coherence.
🔧 Capabilities
- 🎬 Targeted Clip Editing — choose a time range in your video and regenerate only that portion.
- 🎤 Rewrite or replace dialogue while keeping speaker identity and tone.
- 🎥 Modify performance — adjust expressions, gestures, pacing, or emotional delivery.
- 📷 Change camera decisions — adjust pan/zoom, framing, or angle feel.
- 🎧 Refresh audio — update voiceovers, ambient layers, or background music.
- 🔄 Smooth transitions — Retake uses surrounding frames as context for seamless blending.
Perfect for rapid iteration cycles, creative variations, production feedback loops, and marketing experimentation.
📦 Input Parameters
| Parameter | Description |
|---|---|
| video* | Original clip to revise (≤ 100 MB). |
| start_time / end_time | Select a region to edit (min 2s, max 16s). |
| prompt* | Describe changes: acting style, camera motion, energy, tone, audio adjustments. |
Output resolution currently fixed at 1080p.
💰 Pricing
Pricing is determined based on the length of the edited segment. Longer replacement regions cost more, while very short adjustments are priced at a minimum threshold.
Example estimates:
| Segment Length | Approx. Cost |
|---|---|
| 2–5s | Minimum pricing tier |
| 10s | ~2× minimum tier |
| 16s | Higher-tier segment cost |
🎯 Ideal Use Cases
- Reshoot alternatives without crew or scheduling
- Iterate on performance or emotional tone
- Create alternate ad or promo variations
- Correct timing or pacing issues
- Replace dialogue or audio environments
- Seamlessly integrate VFX timing adjustments
📌 Notes
- Best used when surrounding frames contain consistent motion/lighting
- Full output render time depends on edit complexity
✨ Why Retake?
Because high-quality revision shouldn’t require starting over.
Retake gives you surgical creative control — fast, flexible, and production-friendly.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/lightricks/ltx-2-retake" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"mode": "replace_audio_and_video"
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| video | string | Yes | - | The video for generating the output. | |
| mode | string | No | replace_audio_and_video | replace_audio_and_video, replace_audio, replace_video | Mode of operation. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |