Luma Ray 3.2 Text To Video API Documentation

Luma Ray 3.2 Text To Video API Documentation

Playground

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, and duration. 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.

Features

Luma Ray 3.2 Text-to-Video generates cinematic videos from natural-language prompts with selectable aspect ratio, resolution, duration. It is suitable for story-driven scenes, ad concepts, cinematic previsualization, social content, and other prompt-based video generation workflows.

Why Choose This?

• 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.

• Production-ready workflow
  Useful for trailers, short-form storytelling, creative prototyping, and commercial concept videos.

Parameters

How to Use

1. Write your prompt — describe the subject, setting, action, camera movement, lighting, and mood you want.
2. Choose size — select the aspect ratio that fits your target platform or layout.
3. Choose resolution — use 540p for the lowest cost, 720p for a middle option, or 1080p for the highest quality.
4. Choose duration — select either 5s or 10s.
5. Submit — run the model and download the generated video.

Example Prompt

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

Pricing depends on duration and resolution.

Billing Rules

• Base price is $0.50 for a 5s video at 540p
• 10s costs 2× the 5s rate
• 720p costs 2× the 540p rate
• 1080p costs 4× the 540p rate
• Pricing depends only on duration and resolution

Best Use Cases

• Cinematic scene generation — Create short dramatic or emotional video moments from prompts.
• Trailer concepts — Prototype story beats and visual sequences quickly.
• Social media content — Generate short-form video ideas for vertical or widescreen publishing.
• Advertising concepts — Build mood-driven commercial shots before full production.
• Creative previsualization — Test scene direction, pacing, and camera ideas.

Pro Tips

• Be specific in your prompt about subject motion, camera movement, lighting, and emotional tone.
• Use 5s for fast concept validation, then switch to 10s when you need more scene development.
• Start with 540p or 720p for testing and move to 1080p for higher-end final outputs.
• Keep prompts focused on what should happen in the clip rather than listing unrelated visual details.

Notes

• prompt is required.
• duration currently supports 5s and 10s.
• Pricing depends only on the selected duration and resolution.

Related Models

• Luma image-to-video workflows — Useful when you want to animate a starting image instead of generating directly from text.
• Luma video editing workflows — Useful when you want to transform an existing video rather than create one from scratch.
• Prompt-based video generation workflows — Useful when you want alternative quality, cost, or motion styles.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "size": "16:9",
  "resolution": "540p",
  "duration": 5
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/luma/ray-3.2/text-to-video" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters