audiostringrequired
URL of the audio file to generate a video from. Duration must be between 2 and 20 seconds. Must be publicly accessible or base64 data URI.
LTX 2.3 Pro Audio to Video
lightricks/ltx-2.3-pro/audio-to-videoLtx 2.3 Pro Audio To Video by Lightricks - advanced AI model for audio-to-video. Delivers high-quality results with fast inference, suitable for both creative and production workflows.
Try the model
Playground
Input
Text description of how the video should be generated. Required if image_url is not provided. When image_url is provided, this describes how the image should be animated.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
URL of an image to use as the first frame of the video. If not provided, prompt is required.
This field is required.
URL of the audio file to generate a video from. Duration must be between 2 and 20 seconds. Must be publicly accessible or base64 data URI.
Additional Settings More
Customize your input with more control.
Output aspect ratio. Omit to match the input media. Allowed values: 16:9, 9:16.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "audio": "https://static.sandbase.ai/examples/d329ed93-dcc3-4816-a380-9ef3c56b9ed8/input/033e9797-2daf-4d8b-aae3-74eee1a9b8d6.mp3", "image": "https://static.sandbase.ai/examples/d329ed93-dcc3-4816-a380-9ef3c56b9ed8/input/c790a0f6-daad-468d-ad20-666837bc95ba.png", "prompt": "A woman whispering to the microphone" }
LTX 2.3 Pro Audio to Video
LTX 2.3 Pro audio-to-video: animate an image into a video that follows an audio track, such as a voice or song.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 5,000 characters. |
image | image URL, required | — | Image to animate. JPEG, PNG, or WebP URL. |
audio | audio URL, required | — | Audio that drives the video. |
aspect_ratio | 16:9 / 9:16 | — | Output frame shape. |
Billing
$0.10 per output second; the output is as long as the audio. The quote before submission assumes 5 seconds.
| Audio | Price |
|---|---|
| 5s audio | $0.50 |
| 10s audio | $1.00 |
| 20s audio | $2.00 |
Failed runs are not charged.
Prompting
- Describe the scene and motion; timing follows the audio.
Also on SandBase
Other LTX 2.3 endpoints: lightricks/ltx-2.3-pro/text-to-video, lightricks/ltx-2.3-pro/image-to-video, lightricks/ltx-2.3-pro/retake, lightricks/ltx-2.3-pro/video-extend.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "lightricks/ltx-2.3-pro/audio-to-video",
"audio": "https://static.sandbase.ai/examples/lightricks/ltx-2.3-pro/audio-to-video/output_url_1.mp3",
"image": "https://static.sandbase.ai/examples/lightricks/ltx-2.3-pro/audio-to-video/input_image_0.png",
"prompt": "A woman whispering to the microphone"
}
SANDBASE_JSON
)
run_id=$(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
imagestringrequired
URL of an image to use as the first frame of the video. If not provided, prompt is required.
promptstringrequired
Text description of how the video should be generated. Required if image_url is not provided. When image_url is provided, this describes how the image should be animated.
aspect_ratiostring
Output aspect ratio. Omit to match the input media.
Possible values: "16:9", "9:16"
{
"model": "lightricks/ltx-2.3-pro/audio-to-video",
"audio": "https://static.sandbase.ai/examples/lightricks/ltx-2.3-pro/audio-to-video/output_url_1.mp3",
"image": "https://static.sandbase.ai/examples/lightricks/ltx-2.3-pro/audio-to-video/input_image_0.png",
"prompt": "A woman whispering to the microphone"
}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/9323c8905677ae620181.jpg",
"source": "Lightricks/LTX schema mirror",
"source_url": "https://ltx.studio/",
"url": "https://static.sandbase.ai/examples/d329ed93-dcc3-4816-a380-9ef3c56b9ed8/output/ca045116-8299-421a-9398-063d666ef469.mp4"
}
]