LTX-2 19b is the first DiT-based audio-video foundation model with synchronized audio and video, high fidelity, multiple performance modes, and production-ready outputs in one model. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Boşta
$0.08çalıştırma başına·~12 / $1
Stop-motion clay astronaut plants a flag on a tiny moon set. Soft clay squish, miniature wind, tiny crunching steps. Fixed camera, charming imperfections.
A sleek wireless earbud rotates on a glossy pedestal in a white studio. Subtle whoosh transitions, faint electronic hum, clicky case open/close sounds. Macro close-ups, crisp lighting.
Ultra-realistic luxury interior photography, cold bronze used as refined accent material, softly brushed cold bronze surfaces integrated into walls, fireplace surround and custom furniture, warm metallic reflections, elegant contemporary interior design, modern cubist house, sophisticated yet welcoming atmosphere, curated high-end decor objects, organic shapes, premium materials (stone, natural wood, textured fabrics), balanced composition, normal ceiling height, depth in the space with subtle background details, distant window more than 4 meters away with discreet linen curtains barely visible and not emphasized, natural daylight mixed with soft architectural lighting, realistic shadows, rich textures, luxury interior design editorial style, photographed with a professional full-frame camera, 35mm lens, shallow depth of field, extreme photorealism, no people, no text
Hands warming near Lohri bonfire at a luxury hotel, flying sparks, woolen sleeves, night winter ambience, soft firelight on skin, cinematic close-up, cozy festive mood, ultra realistic photography, Indian winter festival
high fashion studio shoot, minimalism, photorealism, tall woman walking forward, full body, long shot, neutral gray concrete background, soft diffused daylight, clean shadows, outfit: beige oversized sweater dress with large cable knit, asymmetrical off-the-shoulder, long textured sleeves, high black suede over-the-knee sock boots, form-fitting, just above the knees, large suede tote bag in matching tone, hair slickly pulled back, minimal makeup, confident stride, elegant pose, high detail on knitwear and leather, realistic textures, sharp focus, monochrome beige-sand palette
LTX-2 is the first DiT-based (Diffusion Transformer) audio-video foundation model, capable of generating synchronized audio and video from a text prompt. With 19 billion parameters, it produces high-fidelity, production-ready clips with natural sound that matches the visuals — no post-production audio layering required.
Synchronized audio-video generation Outputs video with matching audio in a single pass — footsteps, ambient sounds, speech-like tones, and environmental audio are generated to fit the visual content.
High-fidelity visuals Leverages a 19B-parameter DiT architecture for detailed, temporally consistent video with minimal flickering.
Flexible resolution and aspect ratio Supports 480p, 720p, and 1080p outputs in both 16:9 (landscape) and 9:16 (vertical) formats.
Variable duration Generate clips from 5 to 20 seconds, suitable for quick loops or longer narrative beats.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the scene, action, and audio cues |
| resolution | No | Output resolution: 480p, 720p (default), or 1080p |
| aspect_ratio | No | Output format: 16:9 (default) or 9:16 |
| duration | No | Video length in seconds (5-20) |
| seed | No | Random seed for reproducibility (-1 for random) |
| Resolution | Best For |
|---|---|
| 480p | Fast previews, iteration, lowest cost |
| 720p | Balanced quality and cost (default) |
| 1080p | Final delivery, maximum detail |
| Aspect Ratio | Use Case |
|---|---|
| 16:9 | Landscape, YouTube, desktop |
| 9:16 | Vertical, TikTok, Stories, Reels |
| Resolution | 5s | 10s | 15s | 20s |
|---|---|---|---|---|
| 480p | $0.06 | $0.12 | $0.18 | $0.24 |
| 720p | $0.08 | $0.16 | $0.24 | $0.32 |
| 1080p | $0.12 | $0.24 | $0.36 | $0.48 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2-19b/text-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Ltx 2 19b Text To Video below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 5,
"seed": -1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2-19b/text-to-video" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2-19b/text-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 5,
"seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 5,
"seed": -1
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2-19b/text-to-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Ltx 2 19b Text To Video is a WaveSpeedAI model for video generation, exposed as a REST API on WaveSpeedAI. LTX-2 19b is the first DiT-based audio-video foundation model with synchronized audio and video, high fidelity, multiple performance modes, and production-ready outputs in one model. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
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 result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/ltx-2-19b-text-to-video.
Ltx 2 19b Text To Video starts at $0.080 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.
Key inputs: `prompt`, `aspect_ratio`, `resolution`, `duration`, `seed`. 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/wavespeed-ai/ltx-2-19b-text-to-video.
Median end-to-end generation time on WaveSpeedAI is around 32 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.