Gemini Omni 1.1 Flash Text-to-Video API

google/gemini-omni-1.1-flash/text-to-video

Gemini Omni 1.1 Flash (Text-to-Video) turns text prompts into short videos with native audio, camera and lighting control, and output from 360p to 4K. Direct scenes, action, and sound in one creative brief to produce 4–10 second clips for product concepts, storyboards, and social content.

Input

Prompt

564/20000

Resolution

Duration

Aspect ratio

Output

Idle

Your generated video will appear here

Add your prompt and required media, review the settings, then click Run.

Continue with

Gemini Omni 1.1 Flash Image-to-Video Gemini Omni 1.1 Flash Reference-to-Video Gemini Omni 1.1 Flash Video Edit

Examples

One continuous 8-second cinematic shot. Slow push-in down a wet-asphalt night avenue lined with neon storefronts; rain beads on the pavement and a metal awning. No people in close-up, no shops selling products, no readable signs. Lighting: high-contrast neon magenta and teal bouncing off black puddles. Camera: locked-axis slow dolly-in at chest height, no cuts. Native audio: rain on metal, distant traffic hiss, and a low analog music pulse. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.

Vertical 9:16, 4 seconds. Dawn on a weathered wooden fishing pier, pale peach sky, no rain, no city. One adult fisherman in a plain grey jacket stands at the rail, backs three-quarter to camera, and says one short quiet line in English: "The tide is turning." Camera: gentle handheld hold, slight drift, no cuts. Lighting: cool marine dawn with a warm horizon band. Native audio: one spoken line, sea wind, water slapping pilings. Not a cafe, shop, or product scene. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.

One continuous 4-second 16:9 macro shot. A single clear glass marble rolls along a brushed-steel toy track, tapping each joint. Low camera two centimeters above the rail, tracking beside the marble. Lighting: hard workshop sidelight, sharp highlights on glass and metal. Native audio: precise Foley of glass on steel, tiny ticks, quiet room tone. No hands, no toys as products, no packaging. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.

REST API

Quick Start

Authenticate with the API, submit the inputs and instructions, then retrieve the video using the task ID.

Connect to the Vidgo API

Create an API key, keep it only on your server, and send Authorization: Bearer VIDGO_API_KEY.

Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authentication: Authorization: Bearer VIDGO_API_KEY

Submit one generation task

Fill in the inputs and settings for this endpoint using the request example, then save the returned task_id to query generation progress and results.

Submit request

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "google/gemini-omni-1.1-flash/text-to-video",
  "input": {
    "prompt": "One continuous 8-second cinematic shot. Slow push-in down a wet-asphalt night avenue lined with neon storefronts; rain beads on the pavement and a metal awning. No people in close-up, no shops selling products, no readable signs. Lighting: high-contrast neon magenta and teal bouncing off black puddles. Camera: locked-axis slow dolly-in at chest height, no cuts. Native audio: rain on metal, distant traffic hiss, and a low analog music pulse. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.",
    "duration": 8,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }
}
JSON
)

RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

CODE=$(printf '%s' "$RESPONSE" | jq -r '.code // empty')
if [ "$CODE" != "0" ] && [ "$CODE" != "200" ]; then
  printf 'API error: %s
' "$RESPONSE" >&2
  exit 1
fi
printf '%s
' "$RESPONSE"

Wait for the result

Query with task_id, continue for not_started/running, and stop for finished/failed. On success, read data.files[].file_url.

Track status

GET https://api.vidgo.ai/api/generate/status/{task_id}

Poll status with a 2-second base interval, and increase the interval for longer tasks. Continue only while status is not_started or running, and stop once finished or failed. You can also specify callback_url in the request payload to receive webhook notifications.

not_startedrunningfinishedfailed

Submit response

{
  "code": 200,
  "data": {
    "task_id": "task-unified-...",
    "status": "running",
    "created_time": "2026-09-15T10:00:00Z"
  }
}

Finished response

{
  "code": 200,
  "data": {
    "task_id": "task-unified-...",
    "status": "finished",
    "files": [
      {
        "file_url": "https://storage.vidgo.ai/generated/video.mp4",
        "file_type": "video"
      }
    ],
    "created_time": "2026-08-22T10:00:00Z",
    "progress": 100,
    "error_message": null
  }
}

Complete runnable example

Expand for a complete script with HTTP and business-code checks, task_id validation, polling, terminal-state handling, and a timeout boundary.

Complete runnable example

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "google/gemini-omni-1.1-flash/text-to-video",
  "input": {
    "prompt": "One continuous 8-second cinematic shot. Slow push-in down a wet-asphalt night avenue lined with neon storefronts; rain beads on the pavement and a metal awning. No people in close-up, no shops selling products, no readable signs. Lighting: high-contrast neon magenta and teal bouncing off black puddles. Camera: locked-axis slow dolly-in at chest height, no cuts. Native audio: rain on metal, distant traffic hiss, and a low analog music pulse. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.",
    "duration": 8,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
BUSINESS_CODE=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.code // empty')
if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
  printf 'Submit failed:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

START_TIME=$(date +%s)
POLL_DELAY=2
while true; do
  if [ $(( $(date +%s) - START_TIME )) -ge 600 ]; then
    printf 'Timed out after 600 seconds
' >&2
    exit 1
  fi
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')
  BUSINESS_CODE=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.code // empty')
  if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
    printf 'Status request failed:
%s
' "$STATUS_RESPONSE" >&2
    exit 1
  fi

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep "$POLL_DELAY"
      if [ "$POLL_DELAY" -lt 10 ]; then POLL_DELAY=$((POLL_DELAY + 1)); fi
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Input parameters

The table lists available input parameters, types, and defaults. Request examples also include the required top-level model field. Prepare the inputs for this task and configure the output.

Field	Type	Required	Default	Description
prompt	string	Yes	—	1–20,000 characters after trimming.
duration	integer	No	8	4, 6, 8, or 10, in seconds.
resolution	string	No	720p	360p, 720p, 1080p, or 4k.
aspect_ratio	string	No	16:9	16:9 or 9:16.

Response Fields

A successful submission returns a task ID. Status queries provide progress, output files, and error details when a task fails.

Field	Type	Description
code	integer	Application result code; successful responses use 0 or 200.
message	string	Human-readable message or error detail when present.
data.task_id	string	Task ID used in the status endpoint path.
data.status	string	not_started, running, finished, or failed.
data.created_time	string	Task creation time in date-time format.
data.progress	integer	Task progress from 0 to 100, when included in the response.
data.files[]	array	All output files from a successful task, in response order.
data.files[].file_url	string	Public URL for a generated video.
data.files[].file_type	string	File type, such as video.
data.error_message	string \| null	Failure detail when status is failed.

Task Lifecycle

Continue querying while the status is not_started or running. End polling at finished or failed, then process the output files or error details respectively.

not_started
The task was accepted and is waiting to begin.
running
Generation is in progress. Continue polling the same task_id.
finished
Generation succeeded. Read every video URL from data.files[].file_url.
failed
Generation stopped with an error. Read data.error_message and stop polling.

Polling and Errors

AuthenticationFor a 401 response, check the Bearer API key in Authorization, update the credentials, and retry.
ValidationFor a 400 response, use the response details to check required inputs, parameter values, and available credits, then make the indicated adjustments before submitting again.
Network and timeoutIf a status query encounters a network error or timeout, retain the original task_id and retry the query, then handle the result according to the returned task status.
Polling intervalPoll status with a 2-second base interval, and gradually increase the interval for longer tasks.
Terminal statesContinue only for not_started or running. Stop immediately on finished or failed.
Callback optionProvide callback_url at the request top level to receive the final flat task object; polling remains available if delivery fails.

Endpoint limits

Specification	Value	Details
Input mode	Text only	A prompt defines the scene, camera, lighting, mood, and sound.
Output	Video with native audio	The endpoint returns an asynchronous task ID; finished tasks include a video file.
Resolution	360p / 720p / 1080p / 4k	Default is 720p.
Duration	4 / 6 / 8 / 10 seconds	Default is 8 seconds.
Aspect ratio	16:9 / 9:16	Default is 16:9.
Billing basis	Per generation	360p–1080p: 4s=45, 6s=60, 8s=75, 10s=90 credits. 4k: 4s=105, 6s=120, 8s=135, 10s=150 credits.

View Gemini Omni 1.1 Flash Text-to-Video API documentation

Gemini Omni 1.1 Flash Text-to-Video

Gemini Omni 1.1 Flash Text-to-Video turns text prompts into short videos with speech, music, and ambient sound. Describe subject action, camera movement, lighting, and audio to bring product ideas, story scenes, and brand atmospheres into moving footage.

Why Choose This?

Text-driven scene creationBuild a scene through descriptions of subjects, surroundings, and action, turning a product idea or story moment into a watchable clip.
Camera movement controlDescribe push-ins, tracking shots, orbits, and shot sizes to direct attention toward product details or key story moments.
Lighting and atmosphereSpecify light sources, color, and mood to explore morning light, neon streets, or soft interiors around the same creative idea.
Native speech and soundCreate dialogue, music, and ambient sound alongside the video, planning visual content and its soundtrack in one prompt.
Multiple output resolutionsChoose 360p, 720p, 1080p, or 4K to match the output specifications for previews, editing, and content delivery.
Landscape and portrait clipsCombine 16:9 or 9:16 framing with a 4, 6, 8, or 10 second duration to plan composition and pacing for landscape stories or portrait social content.

Parameters

Parameter	Requirement	Description
prompt	Required	String. Defines the scene, action, camera, lighting, mood, and sound; 1–20,000 characters after trimming.
duration	Optional	Integer. Sets output length; the Playground preselects 8 seconds. Default`84610`
resolution	Optional	String. Sets output resolution; the Playground preselects 720p. Default`720p360p1080p4k`
aspect_ratio	Optional	String. Controls output framing; the Playground preselects 16:9. Default`16:99:16`

How to Use

Describe the scene and actionEnter a subject, setting, and main action, such as a glass marble rolling along a metal track beside a warm desk lamp.
Add camera and sound directionDescribe camera movement, lighting, and speech, music, or ambient sound, such as a low tracking shot accompanied by crisp rolling sounds.
Choose a resolutionChoose 360p, 720p, 1080p, or 4K, with 720p selected by default, to match the output specifications for editing or presentation.
Choose a durationChoose 4, 6, 8, or 10 seconds, with 8 seconds selected by default, to plan the clip around its main action and pacing.
Choose an aspect ratioChoose 16:9 landscape or 9:16 portrait, with 16:9 selected by default, and frame the subject for the intended layout.
Review the cost and runReview the cost shown on the Run button, complete the required uploads and prompt, then click Run.
Preview and download the videoWhen the task finishes, preview the video and sound in the output panel, then select Download video to save the result.

Pricing

Billed per generation based on video duration and resolution tier, with native audio included in the result. 1 credit = $0.005.

Usage	Rate	Details
360p / 720p / 1080p	4s=45, 6s=60, 8s=75, 10s=90 credits	Default 720p / 8s costs 75 credits ($0.375).
4k	4s=105, 6s=120, 8s=135, 10s=150 credits	4k / 8s costs 135 credits ($0.675).

Best Use Cases

Product concept filmsDescribe a product scene, key action, and musical direction to create concept footage for creative pitches and brand presentations.
Storyboard previewsTurn one action beat from a script into a clip with sound to communicate shot size, camera movement, and staging.
Portrait brand contentBuild a scene around one brand theme and choose 9:16 framing to create portrait footage for social channels.
Atmospheric footageCombine rain, streets, or interior lighting with ambient sound to create clips for an opening sequence or story transition.

Pro Tips

Organize the prompt around subject and setting, action, camera, lighting, and audio so each part has a clear creative role.
Describe subject action and camera movement separately, such as “The person walks toward the door. The camera tracks slowly from the side,” to define how they relate.
For a continuous shot, specify the starting camera position, direction of travel, and final composition.
Introduce speech, music, and effects with “Audio:” and connect sounds to actions, such as a hinge creaking as a door opens.
Build each 4–10 second clip around one main action, describing its opening state, progression, and closing image.

Usage notes

Gemini Omni 1.1 Flash Text-to-Video generates video from a required text prompt (prompt), with duration, resolution, and aspect ratio settings to configure the output.
Describe speech, music, or ambient sound in the prompt; native audio is included in the result.
Provide a prompt of 1–20,000 characters after trimming, describing the scene, action, camera, and sound.
Save the task_id returned by an API submission to query progress and retrieve the result.

Gemini Omni 1.1 Flash Reference-to-VideoUse 1–7 reference images to guide characters, products, and visual style in a new scene.

Gemini Omni 1.1 Flash Video EditEdit a 3–10 second source clip through natural language, describing changes and content to retain.

Veo 3.1Use Google DeepMind Veo 3.1 for text and image video workflows with native audio.

Seedance 2.5Compare a ByteDance family with text, start/end-frame, and multimodal reference workflows.

MiniMax H3Compare a fixed 2K video family with text, frame, and multimodal reference workflows.

Gemini Omni 1.1 Flash Text-to-Video API frequently asked questions

What is the Gemini Omni 1.1 Flash Text-to-Video API?

Gemini Omni 1.1 Flash Text-to-Video is a Google model for generating video from text. It creates short videos up to 4K resolution with native dialogue, music, and ambient sound effects from text prompts, supporting precise camera movement, lighting, and atmospheric scene control. Built on Gemini's multimodal intelligence architecture, it strictly follows prompt physics and visual continuity while delivering cinematic narrative pacing. You can call it programmatically or try it from the playground above.

Can Gemini Omni 1.1 Flash Text-to-Video generate speech and music?

Yes. The model features native audio-visual synchronization without requiring post-production audio synthesis. By describing dialogue lines, musical moods, or ambient sound effects (such as footsteps or raindrops) in your prompt, the model embeds synchronized audio tracks directly into the output MP4 video.

What is the maximum duration for a single Gemini Omni 1.1 Flash Text-to-Video generation?

A single call supports generating clips up to 10 seconds, with choices of 4, 6, 8, or 10 seconds (the playground defaults to 8 seconds). For narratives requiring broader story arcs, you can structure sequential story beats cleanly within the prompt or extend shots progressively using continuation workflows.

Does Gemini Omni 1.1 Flash Text-to-Video support 4K resolution?

Yes. The model provides output resolution tiers from 360p, 720p, and 1080p up to 4K. 4K mode is ideal for high-end commercial showcases and final delivery by preserving fine lighting reflections and surface textures, whereas 720p offers a balanced preview experience for daily iteration.

Can I use 360p to rapidly prototype Gemini Omni 1.1 Flash Text-to-Video concepts?

Yes. The 360p resolution is designed specifically for low-latency drafting, significantly accelerating generation speed and reducing credit consumption. You can validate staging, subject movement, and camera timing in 360p drafts before switching to 1080p or 4K for production rendering.

How do I direct camera movement in Gemini Omni 1.1 Flash Text-to-Video?

We recommend separating subject choreography and camera directions into distinct sentences within your prompt. Using explicit cinematographic terms such as slow dolly forward, 360-degree orbit, or low-angle tracking shot, combined with specific lighting cues (like warm side lighting or neon reflections), produces controlled and coherent motion.

Is Gemini Omni 1.1 Flash Text-to-Video suitable for 9:16 vertical videos?

Yes. The model supports standard 16:9 landscape and 9:16 portrait aspect ratios. When selecting 9:16, focus prompt descriptions on vertical composition and subject positioning, allowing the model to naturally optimize focal balance and background framing for mobile feeds.