Google Veo3.1 Fast Reference To Video API Documentation

Google Veo3.1 Fast Reference To Video API Documentation

Playground

Google Veo 3.1 Fast Reference to Video is a fast AI reference-to-video generation model that creates 8-second videos from up to three reference images using the official Veo predictLongRunning endpoint with referenceImages assets. Ready-to-use REST inference API for product videos, character consistency, branded visual storytelling, social media clips, advertising creatives, and professional reference-based video generation workflows with simple integration, no coldstarts, and affordable pricing.

Features

Google Veo 3.1 Fast Reference-to-Video generates an 8-second video guided by up to three reference images and a text prompt. It is designed for subject, object, and product consistency, making it useful for character-led shots, product motion, style-guided generation, and other reference-driven video workflows.

Why Choose This?

• Reference-guided generation Use up to three reference images to preserve subject, object, or product identity in the generated video.

• Fast Veo workflow Built on Google Veo 3.1 Fast for quicker turnaround and efficient iteration.

• Consistent 8-second output Generates a fixed-length 8s MP4, making duration predictable for planning and pricing.

• Flexible aspect ratio Supports both 16:9 and 9:16 for landscape and vertical video use cases.

• Optional audio generation Enable generate_audio when you want the output to include generated sound.

• Simple pricing Pricing depends only on resolution and whether audio generation is enabled.

Parameters

How to Use

1. Upload your reference images — provide 1–3 images for subject, style, or product guidance.
2. Write your prompt — describe the motion, scene progression, camera movement, and overall visual intent.
3. Set aspect ratio — choose 16:9 for landscape or 9:16 for vertical output.
4. Choose resolution — use 720p for lower cost or 1080p for higher quality.
5. Enable audio (optional) — turn on generate_audio if you want generated sound in the result.
6. Add a negative prompt (optional) — describe elements or artifacts you want to avoid.
7. Set a seed (optional) — use a fixed seed for more reproducible outputs.
8. Submit — run the model and download the generated 8-second video.

Example Prompt

A cinematic product reveal of the same luxury watch from the reference images, rotating slowly on a reflective black surface, dramatic studio lighting, soft camera push-in, premium commercial style

Pricing

This model generates a fixed 8-second video.

Billing Rules

• Output length is fixed at 8 seconds
• 720p without audio costs $0.64
• 720p with audio costs $0.80
• 1080p without audio costs $0.80
• 1080p with audio costs $0.96
• Pricing depends only on resolution and generate_audio
• aspect_ratio, negative_prompt, seed, and the number of reference images do not affect pricing

Best Use Cases

• Product motion videos — Generate controlled product shots from reference images.
• Character consistency — Keep the same subject identity across a short generated clip.
• Style-guided generation — Use references to anchor visual style, mood, or composition.
• Marketing creatives — Produce short polished clips for ads, social media, and promotional assets.
• Vertical content — Generate 9:16 outputs for short-form mobile platforms.

Pro Tips

• Use clear, high-quality reference images for stronger identity preservation.
• Keep the reference images visually consistent when you want the subject or product to remain stable.
• Be specific in your prompt about motion, camera movement, and scene intent.
• Use negative_prompt to reduce unwanted style drift or artifacts.
• Enable audio only when you actually need it, since it changes pricing.
• Reuse the same seed when you want more reproducible generations.

Notes

• Both prompt and images are required.
• This workflow supports up to 3 reference images.
• The model uses the official Veo 3.1 Fast long-running generation flow with referenceImages added to the request payload.
• Output duration is fixed at 8 seconds.
• generate_audio defaults to false.

Related Models

• Other Google Veo 3.1 Fast video generation variants may be useful when you need text-to-video or non-reference workflows.

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",
  "images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "generate_audio": false,
  "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/google/veo3.1-fast/reference-to-video" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  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
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters