promptstringrequired
The prompt to use for the generated video
LTX 2.3 Fast Text to Video
lightricks/ltx-2.3-fast/text-to-videoLtx 2.3 Fast by Lightricks - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.
Try the model
Playground
Input
The prompt to use for the generated video
Additional Settings More
Customize your input with more control.
The aspect ratio of the generated image. Allowed values: 16:9, 9:16.
The resolution of the generated video Allowed values: 1080p, 1440p, 2160p.
The duration of the generated video in seconds. The fast model supports 6-20 seconds. Note: Durations longer than 10 seconds (12, 14, 16, 18, 20) are only supported with 25 FPS and 1080p resolution. Allowed values: 6, 8, 10, 12, 14, 16, 18, 20.
Whether to generate audio for the generated video
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "prompt": "Drone descent through the open oculus of a derelict Soviet-era radio telescope dish, spiraling downward into the rusted parabolic bowl where a lone botanist catalogs wildflowers growing through cracked concrete, her red jacket the only color against oxidized metal and grey sky, 24mm on a caged FPV drone, the descent creating a vertigo spiral, Tarkovsky Stalker zones of alien beauty reclaiming technology, science swallowed by nature" }
Human preference
Arena
Elo ratings from blind side-by-side votes, compared with other image and video models.
Rankings sourced from Artificial Analysis Arena
- Leaderboard
- Text to Video
- Rank
- #29 of 33
- Elo
- 844 ±18
- Gap to #1
- −299
Text-to-video arena (silent): people pick the better of two clips from the same prompt, without seeing the model names; audio is not judged.
- #24LTX-2.5 Pro928±17
- #25Runway Gen-4.5 (720p)909±18
- #26Vidu Q3 Pro900±17
- #27Vidu Q3 Turbo900±17
- #28Kling O1 Pro (January)887±18
- #29LTX-2.3 Fast844±18
- #30LTX-2.3 Pro836±18
- #31Pika 2.5835±19
- #32Boreal822±19
- #33P-Video801±19
LTX 2.3 Fast Text to Video
LTX 2.3 Fast text to video: up to 20 second clips with native audio at 1080p, 1440p, or 4K (2160p).
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 5,000 characters. |
aspect_ratio | 16:9 / 9:16 | 16:9 | Output frame shape. |
resolution | 1080p / 1440p / 2160p | 1080p | Sets the per-second rate. |
duration | 6 / 8 / 10 / 12 / 14 / 16 / 18 / 20 | 6 | Output length in seconds. |
generate_audio | boolean | true | Native audio. |
Billing
You pay for output seconds: $0.06 at 1080p, $0.12 at 1440p, $0.24 at 2160p.
| Output | 1080p | 1440p | 2160p |
|---|---|---|---|
| 6s (default) | $0.36 | $0.72 | $1.44 |
| 10s | $0.60 | $1.20 | $2.40 |
| 20s | $1.20 | $2.40 | $4.80 |
Failed runs are not charged.
Prompting
- Describe subject, action, camera, and sound.
Also on SandBase
Other LTX 2.3 endpoints: lightricks/ltx-2.3-pro/text-to-video, lightricks/ltx-2.3-pro/image-to-video, lightricks/ltx-2.3-pro/audio-to-video, lightricks/ltx-2.3-pro/retake.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "lightricks/ltx-2.3-fast/text-to-video",
"prompt": "Drone descent through the open oculus of a derelict Soviet-era radio telescope dish, spiraling downward into the rusted parabolic bowl where a lone botanist catalogs wildflowers growing through cracked concrete, her red jacket the only color against oxidized metal and grey sky, 24mm on a caged FPV drone, the descent creating a vertigo spiral, Tarkovsky Stalker zones of alien beauty reclaiming technology, science swallowed by nature",
"duration": 6,
"resolution": "1080p",
"aspect_ratio": "16:9",
"generate_audio": true
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
durationinteger
The duration of the generated video in seconds. The fast model supports 6-20 seconds. Note: Durations longer than 10 seconds (12, 14, 16, 18, 20) are only supported with 25 FPS and 1080p resolution.
Default: 6
Possible values: 6, 8, 10, 12, 14, 16, 18, 20
resolutionstring
The resolution of the generated video
Default: "1080p"
Possible values: "1080p", "1440p", "2160p"
aspect_ratiostring
The aspect ratio of the generated image.
Default: "16:9"
Possible values: "16:9", "9:16"
generate_audioboolean
Whether to generate audio for the generated video
Default: true
{
"model": "lightricks/ltx-2.3-fast/text-to-video",
"prompt": "Drone descent through the open oculus of a derelict Soviet-era radio telescope dish, spiraling downward into the rusted parabolic bowl where a lone botanist catalogs wildflowers growing through cracked concrete, her red jacket the only color against oxidized metal and grey sky, 24mm on a caged FPV drone, the descent creating a vertigo spiral, Tarkovsky Stalker zones of alien beauty reclaiming technology, science swallowed by nature",
"duration": 6,
"resolution": "1080p",
"aspect_ratio": "16:9",
"generate_audio": true
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"poster": "https://static.sandbase.ai/examples/posters/d85d133037bc66b4cbf7.jpg",
"source": "Lightricks/LTX schema mirror",
"source_url": "https://ltx.studio/",
"url": "https://static.sandbase.ai/examples/20ca6eae-1cb7-464e-9b85-168cb86d7d18/output/296401b2-83b4-4935-9d5e-7fa06a75532a.mp4"
}
]