Generate or edit MP4 videos with Gemini Omni Flash.

Capabilities:

• text_to_video: prompt-only video with generated audio.

• image_to_video: one reference image plus motion and camera direction.

• reference_to_video: multiple reference images for subjects, style, or props.

• edit: use previous_interaction_id or input_video_path to edit existing video.

Parameters:

• prompt: Describe the scene, motion, camera movement, lighting, mood, and audio.

• task: text_to_video, image_to_video, reference_to_video, or edit. If omitted, inferred.

• aspect_ratio: 16:9 landscape or 9:16 portrait.

• duration_seconds: Optional 3 to 10 second target. If the API rejects this preview field, retry without it.

• reference_image_paths: Up to 6 local images. Use or tags in the prompt for control.

• input_video_path: Local MP4 to upload and edit through the Files API.

• delivery: uri is recommended for generated MP4 files; inline is supported for smaller payloads.

• previous_interaction_id: Continue editing a prior generated video.

• enhance_prompt: Optional, default false. For edits, simple prompts usually work better.

Prompt tips:

• Ask for "single continuous shot" and "no scene cuts" when you want one scene.

• Include explicit audio direction such as "gentle ambient room tone, no dialogue".

• For edits, say "Keep everything else the same".

• Timing cues like [0-3s], [3-6s], [6-10s] are supported.

Limitations:

• Output is MP4, currently 720p at 24fps, SynthID-watermarked, and preview quality.

• System instructions, temperature, top_p, stop sequences, negative_prompt, voice edits, YouTube sources, and multi-video reasoning are unsupported.

• Uploaded-video editing is unavailable in some regions.

Returns JSON including video.path, interaction_id, task, aspect_ratio, delivery, size, and URI metadata. After success, open video.path with the native OS video viewer.

Generate multiple Gemini Omni Flash videos in conservative parallel batches.

Use for storyboards, aspect-ratio comparisons, or reference-guided variations. Batch size defaults to configuration and is capped at 4 because video jobs are long. The JSON response includes per-prompt video.path, interaction_id, metadata, and errors.