Google Veo3 Fast Image To Video API Documentation

Google Veo3 Fast Image To Video API Documentation

Playground

Google Veo3 Fast provides faster, more cost-effective Image-to-Video generation vs Veo 3, with commercial use allowed and $0.25/sec pricing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Veo 3 Fast (I2V) is the high-speed image-to-video variant of Google’s Veo 3 generative suite. It transforms static images into cinematic 1080p motion clips with synchronized native audio — all in a fraction of the time and cost of standard Veo 3.

⚡ Why it stands out

• From Still Image to Story Turn a single reference image into smooth, realistic motion sequences with natural lighting and perspective continuity.

• High Speed, Low Cost Generates videos up to 30 % faster while using 80 % fewer credits, ideal for rapid creative iterations.

• Cinematic Realism Produces expressive camera motion, atmospheric lighting, and lifelike character animation.

• Native Audio Sync Automatically adds ambient sound, subtle effects, and music that match the visual rhythm — no post-production required.

• Style & Identity Consistency Keeps subjects, color tone, and camera direction faithful to the uploaded image for coherent storytelling.

⚙️ Limits and Performance

💰 Pricing

Every run needs $1.2 (both 720p and 1080p)

Without audio needs $0.8

✅ Commercial use allowed

🚀 How to Use

1. Upload an Image Provide a clear, well-lit source image — this defines your main subject and composition.

2. Write a Prompt Describe the desired motion, mood, and camera behavior.

> Example: “Slow cinematic zoom out from the character as wind moves through the trees.”

3. Adjust Settings Choose the duration (up to 8 s) and resolution (up to 1080p).

4. Generate the Video Submit your job — Veo 3 Fast I2V automatically creates the motion and synchronized soundscape.

5. Preview & Download Review your result, refine your prompt if needed, and download the final MP4 file.

💡 Pro Tips

• Use bright, high-contrast source images for clearer motion definition.
• Keep prompts focused on one subject or action to ensure stability.
• Add cinematic cues like “soft daylight,” “slow pan,” or “dramatic backlight” for stylistic control.
• Avoid extreme or conflicting directions (e.g., “zoom in and out simultaneously”).
• For multiple related clips, reuse the same source image for consistent appearance.

📝 Notes

• Actual processing time varies depending on queue load and resolution.
• The model is optimized for short, cinematic sequences and social-media content.
• Ensure your uploaded image is clear, accessible, and properly licensed.
• Please make sure your prompts comply with Google’s Safety Guidelines — if an error appears, revise your prompt and try again.

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",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "aspect_ratio": "16:9",
  "duration": 8,
  "resolution": "720p",
  "generate_audio": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/google/veo3-fast/image-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