Google Veo3.1 Fast Video Extend

Google Veo3.1 Fast Video Extend

Playground

Extend Veo 3.1 videos in 7-second steps with the Fast endpoint—quick, coherent continuation that preserves style and motion, output as a single merged clip. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Veo 3.1 Video Extend (Fast) lets you quickly append a 7-second continuation to an existing Veo-generated video. You pass the previous output as video plus a new prompt, and the model returns one merged clip containing both the original segment and the new extension—optimised for low latency and faster iteration.

⚡ What makes the Fast endpoint different

• Optimised for speed: Same continuation logic as standard Video Extend, but tuned for faster turnaround so you can iterate more quickly.
• True continuation, not regeneration: Works only with Veo 3.1 outputs, preserving look, motion style, and aspect ratio.
• Fixed extension block: Each call adds +7 seconds, and you can chain extensions up to 20 times.
• Single merged deliverable: The API always returns one video file (input + extension) with a maximum length of 148 seconds.

🎯 Designed For

• Rapid story development: Test different “next beats” on top of a strong base shot without re-generating the whole sequence.
• Ad and social variations: Quickly create extended cuts, alternate endings, or extra moments for trailers, promos, and Shorts/Reels.
• Fast production feedback loops: Respond to review notes by extending just the part that needs more room.

🧩 Input / Output Constraints

• Input must be Veo-generated: Upload only videos that were created by Veo 3.1 (text-to-video or image-to-video).

• Input limits:

• Maximum input duration: 141 seconds

• Supported aspect ratios: 16:9 or 9:16

• Supported resolutions: 720p or 1080p

• Extension limits:

• Each run adds +7 seconds

• Maximum final length (original + extensions): 148 seconds

Output: a single MP4 video at the same resolution and aspect ratio as the input clip.

🚀 How to Use

1. Generate a base clip with Veo 3.1 text-to-video or image-to-video.
2. Call Veo 3.1 — Video Extend (Fast) and pass that clip as video.
3. Write an extension prompt describing what should happen next:

• Action (what characters or objects do)
• Camera behaviour (pan, zoom, dolly, cut feel)
• Mood and visual style (lighting, atmosphere, pacing)

4. Submit the job and download the merged extended video.
5. To continue the story, feed the new output back into the same endpoint (respecting the 148s cap).

✍️ Prompt Tips

• Think of the prompt as a “next shot” or “next beat”:

action + camera + mood + continuity anchors

Example: “Continue from previous shot, camera slowly cranes up, the character walks toward the glowing city skyline, warm cinematic lighting, smooth motion.”

• Mention what should stay consistent:

• Main character, wardrobe, time of day, general colour palette.

• If audio continuity matters, ensure the last second of the input clip has usable audio; the extension will build from that context.

• Plan your narrative around:

• 7-second extension blocks, and

• the 141s input / 148s total hard limits.

💰 Pricing

Flat, simple pricing:

• $1.20 per run

Each run appends one 7-second fast extension to your clip and returns a new merged video.

🔁 More Model Options

• /wan-2.5/video-extend Extend WAN 2.5 AI videos with smooth, style-consistent continuations, perfect for story-driven ads, trailers, and long-form generative video workflows.

• google/veo3.1/video-extend Google Veo 3.1 Fast video extend rapidly adds high-quality extra segments to Veo-generated clips, ideal for Shorts, Reels, and other fast-turnaround AI video content.

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'
{
  "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "resolution": "1080p"
}
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/video-extend" \
  -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