Gemini Omni Flash on Google Flow API

Google Flow API v1 now supports Gemini Omni Flash — Google’s audio-native video model with text-to-video, reference-to-video, and a new video editing mode (transform an uploaded MP4 with a prompt).

Field	Value
Endpoint	POST /videos
model	omni-flash
referenceVideo_1	uploaded MP4 (via POST /assets/email)
referenceImage_1..7	image references
referenceAudio_1..5	voice presets for spoken dialogue
aspectRatio	landscape, portrait

Example

Source MP4 → restyled cartoon, same motion and framing:

Source video (referenceVideo_1)

# 1. Upload MP4
curl -X POST 'https://api.useapi.net/v1/google-flow/assets/[email protected]' \
    -H 'Authorization: Bearer user:12345-…' \
    -H 'Content-Type: video/mp4' \
    --data-binary @source.mp4

# 2. Submit edit
curl -X POST 'https://api.useapi.net/v1/google-flow/videos' \
    -H 'Authorization: Bearer user:12345-…' \
    -H 'Content-Type: application/json' \
    --data '{
      "model": "omni-flash",
      "prompt": "Transform the scene into a vibrant animated cartoon style with bright neon colors",
      "referenceVideo_1": "user:…-email:…-video:…",
      "async": true
    }'

# 3. Poll GET /jobs/{jobId} until status: "completed"

Result