Google Gemini Omni 1.1 Flash Video Edit API Documentation

Google Gemini Omni 1.1 Flash Video Edit API Documentation

Playground

Gemini Omni 1.1 Flash Video Edit applies natural-language edits to existing videos, supporting output resolutions from 360P to 4K for prompt-guided video modification, scene refinements, creative edits, marketing content, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Gemini Omni 1.1 Flash Video Edit applies natural-language changes to an existing video while preserving its visual context. Use it to edit subjects, style, scene details, motion, lighting, or camera treatment, then choose a fast preview tier or a higher-resolution delivery tier.

Why Choose This?

• Prompt-guided video editing
  Describe the desired change in natural language instead of building a manual editing workflow.

• Context-aware transformation
  Use the source clip as visual context for subject, scene, motion, and composition.

• Fast preview workflow
  Generate 360p previews when comparing edit directions or testing prompts.

• Flexible resolution options
  Choose 360p, 720p, 1080p, or 4k depending on speed, cost, and output quality needs.

• High-resolution delivery
  Use 1080p or 4k when final output quality matters.

Parameters

How to Use

1. Upload the source video — Provide the video you want to edit. The input is limited to 10 seconds.
2. Write your edit prompt — Describe what should change and what should remain consistent.
3. Choose resolution — Use 360p for fast previews, 720p for standard output, or 1080p / 4k for higher-quality delivery.
4. Submit — Generate the edited video.

Pricing

Pricing is based on source video duration and selected resolution.

Source duration is rounded up to the next whole second, with a minimum billed duration of 3 seconds and a maximum billed duration of 10 seconds.

Example Costs

Best Use Cases

• Video restyling — Change the visual style, mood, lighting, or atmosphere of an existing clip.
• Subject edits — Modify subject appearance, outfit, details, or presentation while keeping scene context.
• Scene refinement — Adjust backgrounds, props, environmental details, or visual tone.
• Creative prototyping — Test different edit directions at 360p before generating higher-resolution outputs.
• Marketing and social content — Adapt short clips for ads, reels, product visuals, and campaign assets.
• High-resolution finishing — Use 1080p or 4k for final delivery when quality matters.

Pro Tips

• Write prompts that clearly describe both what should change and what should remain unchanged.
• Use 360p for fast iteration before moving to higher resolutions.
• Keep edit instructions focused on a specific visual change.
• Mention subject, background, lighting, camera treatment, and style when relevant.
• Use short, clean source clips for more stable edits.
• Avoid asking for too many unrelated changes in one request.

Related Models

• Gemini Omni 1.1 Flash Text-to-Video — Generate videos directly from text prompts with synchronized audio.
• Gemini Omni 1.1 Flash Image-to-Video — Animate a start image into a video with optional last-frame guidance.
• Gemini Omni 1.1 Flash Reference-to-Video — Generate videos using reference media for stronger visual guidance.

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": "720p"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/google/gemini-omni-1.1-flash/video-edit" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 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|deleted) 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