Luma Ray 3.2 Text to Video is a fast AI video generation model that creates cinematic videos from text prompts with controllable aspect ratio, resolution, duration, and optional reference images. Ready-to-use REST inference API for cinematic clips, storytelling videos, social media content, advertising creatives, product visuals, concept videos, and professional text-to-video workflows with simple integration, no coldstarts, and affordable pricing.
निष्क्रिय
$0.5प्रति रन·~20 / $10
A cinematic post-apocalyptic video of a tired father carrying his little daughter through an abandoned city street at sunrise. Broken cars, overgrown plants, and ruined buildings surround them. The daughter wakes up and points at a small butterfly landing on a cracked traffic light. The father stops, smiles faintly for the first time, and gently lowers her to watch it. The camera follows them from behind, then slowly circles to reveal their faces. Warm sunrise light, dust in the air, realistic survival drama, emotional and hopeful tone. No subtitles, no text, no watermark.
Luma Ray 3.2 Text-to-Video generates cinematic videos from natural-language prompts with selectable aspect ratio, resolution, duration, and optional reference guidance. It is suitable for story-driven scenes, ad concepts, cinematic previsualization, social content, and other prompt-based video generation workflows.
Prompt-based video generation
Turn detailed natural-language scene descriptions into generated video clips.
Multiple resolution tiers
Choose 540p, 720p, or 1080p depending on your quality and budget needs.
Simple duration control
Generate either 5s or 10s clips with predictable pricing.
Flexible aspect ratio
Use different size presets such as 16:9 for widescreen output.
Optional reference support
Add references when you want stronger visual guidance for style, subject, or scene direction.
Production-ready workflow
Useful for trailers, short-form storytelling, creative prototyping, and commercial concept videos.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text prompt describing the scene, motion, camera behavior, and visual style. |
| size | No | Output aspect ratio preset, such as 16:9. |
| resolution | No | Output resolution. Supported values: 540p, 720p, 1080p. |
| duration | No | Output duration. Supported values: 5s, 10s. |
| reference | No | Optional reference input for additional visual guidance. |
540p for the lowest cost, 720p for a middle option, or 1080p for the highest quality.5s or 10s.A cinematic post-apocalyptic video of a tired father carrying his little daughter through an abandoned city street at sunrise. Broken cars, overgrown plants, and ruined buildings surround them. The daughter wakes up and points at a small butterfly landing on a cracked traffic light. The father stops, smiles faintly for the first time, and gently lowers her to watch it. The camera follows them from behind, then slowly circles to reveal their faces. Warm sunrise light, dust in the air, realistic survival drama.
Pricing depends on duration and resolution.
| Duration | 540p | 720p | 1080p |
|---|---|---|---|
| 5s | $0.50 | $1.00 | $2.00 |
| 10s | $1.00 | $2.00 | $4.00 |
5s video at 540p10s costs 2× the 5s rate720p costs 2× the 540p rate1080p costs 4× the 540p rateduration and resolution5s for fast concept validation, then switch to 10s when you need more scene development.540p or 720p for testing and move to 1080p for higher-end final outputs.prompt is required.duration currently supports 5s and 10s.duration and resolution.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/luma/ray-3.2/text-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Ray 3.2 Text To Video below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "16:9",
"resolution": "540p",
"duration": "5s"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/luma/ray-3.2/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/luma/ray-3.2/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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "16:9",
"resolution": "540p",
"duration": "5s"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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",
"size": "16:9",
"resolution": "540p",
"duration": "5s"
}
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/luma/ray-3.2/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)Ray 3.2 Text To Video is a Luma model for video generation, exposed as a REST API on WaveSpeedAI. Luma Ray 3.2 Text to Video is a fast AI video generation model that creates cinematic videos from text prompts with controllable aspect ratio, resolution, duration, and optional reference images. Ready-to-use REST inference API for cinematic clips, storytelling videos, social media content, advertising creatives, product visuals, concept videos, and professional text-to-video workflows with simple integration, no coldstarts, and 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/luma/luma-ray-3.2-text-to-video.
Ray 3.2 Text To Video starts at $0.50 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`, `resolution`, `duration`, `size`, `reference`. 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/luma/luma-ray-3.2-text-to-video.
Median end-to-end generation time on WaveSpeedAI is around 41 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 (Luma). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.