FLUX 3 Text to Video API

blackforestlabs/flux-3/text-to-video

FLUX 3 Text to Video turns text prompts into 5–20 second high-fidelity video with physically accurate motion, optional synchronized native audio, and eight framing options. It sustains action and camera continuity across the take while aligning dialogue, effects, and ambient sound with on-screen events.

Input

Prompt

168/20000

Duration

Resolution

Aspect ratio

Sound

Output

Idle

Your generated video will appear here

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

Continue with

FLUX 3 Image to Video FLUX 3 First Last Frame to Video FLUX 3 Extend Video FLUX 3 Keyframes to Video

Examples

One continuous 5-second cinematic shot. A violinist performs in a sunlit stone cathedral, dust motes drifting through tall shafts of morning light. Camera: slow forward dolly at chest height, no cuts. Lighting: warm volumetric sunbeams against cool stone. Native audio: a rich solo violin melody echoing in the stone acoustic space, faint bow texture. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.

One continuous 5-second ultra-wide macro shot. Clear water cascades over mossy basalt steps in a rainforest, droplets scattering off wet stone. Camera: low locked shot two centimeters above the waterline. Lighting: soft canopy-filtered daylight with sparkling highlights. Native audio: close-miked water rush, droplet ticks, distant bird calls. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.

Vertical 9:16, one continuous 5-second shot. A single tumbleweed rolls across a cracked desert playa at dusk, casting a long shadow. Camera: low tracking shot beside the tumbleweed, steady pace. Lighting: low amber sun with purple sky. Native audio: dry stems scraping hardpan, a steady desert wind, one distant coyote call. 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 prompt and settings, 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 parameters for this endpoint using the request example, then save the returned task_id to query progress and results.

Submit request

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "blackforestlabs/flux-3/text-to-video",
  "input": {
    "prompt": "One continuous 5-second cinematic shot. A violinist performs in a sunlit stone cathedral, dust motes drifting through tall shafts of morning light. Camera: slow forward dolly at chest height, no cuts. Lighting: warm volumetric sunbeams against cool stone. Native audio: a rich solo violin melody echoing in the stone acoustic space, faint bow texture. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "sound": true
  }
}
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": "2026-09-16T10:00:00Z"
  }
}

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": "blackforestlabs/flux-3/text-to-video",
  "input": {
    "prompt": "One continuous 5-second cinematic shot. A violinist performs in a sunlit stone cathedral, dust motes drifting through tall shafts of morning light. Camera: slow forward dolly at chest height, no cuts. Lighting: warm volumetric sunbeams against cool stone. Native audio: a rich solo violin melody echoing in the stone acoustic space, faint bow texture. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "sound": true
  }
}
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 prompt and configure the output.

Field	Type	Required	Default	Description
prompt	string	Yes	—	minLength 1. Describes scene, subject action, camera movement, and native audio.
duration	integer	No	5	Output duration in seconds from 5 to 20.
resolution	string	No	720p	Output resolution: 720p or 1080p.
aspect_ratio	string	No	auto	Framing ratio: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, or 9:16.
sound	boolean	No	true	Whether to generate native synchronized audio.

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 fields, parameter ranges, and available credits, then adjust and resubmit.
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 prompt	Natural language instructions for scene, camera, and sound.
Output	Video with optional native audio	Returns an asynchronous task ID; sound enabled includes synchronized audio.
Duration	5–20 seconds	Integer range, default 5 seconds.
Resolution	720p / 1080p	Default is 720p.
Aspect ratio	8 options (including auto)	auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16; default auto.
Billing basis	Output seconds × resolution rate	34 credits/sec for 720p, 58 credits/sec for 1080p.

View FLUX 3 Text to Video API documentation

FLUX 3 Text to Video

FLUX 3 Text to Video generates cinematic video and synchronized native audio directly from text prompts. With accurate physical motion simulation, it supports 5–20 second continuous takes, eight aspect ratios, and 720p / 1080p output for professional storytelling and high-quality production.

Why Choose This?

Accurate physical motion simulationRenders fluid dynamics, cloth movement, organic body mechanics, and material reflections with natural real-world behavior.
Native synchronized multi-track audioGenerates matching dialogue, foley, ambience, and score cues with the picture, with independent on/off control via sound.
Extended 5–20 second generationProduces continuous video from 5 up to 20 seconds in a single run while maintaining camera momentum and narrative continuity.
Eight flexible aspect ratiosCovers cinematic 21:9 through vertical 9:16, plus intelligent auto composition matching for multi-platform delivery.
Deep camera and timeline adherenceFollows detailed directorial instructions such as dolly moves, pans, orbits, and sequential beat progressions.
Crisp 720p and 1080p tiersOffers high-definition output for both rapid creative iteration and final production delivery.

Parameters

Parameter	Requirement	Description
prompt	Required	String with minLength 1. Directs scene, subject motion, camera movement, and native audio.
duration	Optional	Integer. Sets output length from 5 to 20 seconds; the Playground preselects 5 seconds. Default`5`
resolution	Optional	String. Sets output resolution; the Playground preselects 720p. Default`720p1080p`
aspect_ratio	Optional	String. Controls framing; the Playground preselects auto. Default`auto21:92:116:94:31:13:49:16`
sound	Optional	Boolean. Controls whether native synchronized audio is generated; the Playground preselects true. Default`truefalse`

How to Use

Write the scene promptDescribe subject action, lighting, camera movement, and the native audio you want in the shot.
Choose output durationSet a length between 5 and 20 seconds based on pacing needs; default is 5 seconds.
Select resolution tierChoose 720p or 1080p depending on turnaround versus visual fidelity; default is 720p.
Select aspect ratioPick 16:9, 9:16, 21:9, auto, or another of the eight framing options to match your distribution layout.
Configure audio generationLeave sound set to true for synchronized audio, or set it to false for silent footage.
Review the cost and runReview the cost shown on the Run button, finish the prompt and settings, then click Run.
Preview and download the videoWhen the task finishes, preview picture and sound in the output panel, then select Download video to save the result.

Pricing

Billed by output video seconds and resolution tier, with native synchronized audio included in the result. 1 credit = $0.005.

Usage	Rate	Details
720p	34 credits/sec ($0.17/sec)	Default 5s at 720p is 170 credits ($0.85).
1080p	58 credits/sec ($0.29/sec)	5s at 1080p is 290 credits ($1.45).

Best Use Cases

Cinematic visual previsualizationGenerate concept clips with detailed camera trajectories and lighting to validate shot pacing and blocking.
Commercial and promotional creativeProduce visually compelling brand concepts paired with synchronized audio environments.
Short-form and social storytellingCreate high-impact vertical content in 9:16 with native dialogue and sound effects.
Natural environments and physics dynamicsRender moving water, weather, and particle motion accompanied by matching ambient sound.
Audiovisual atmosphere shotsCombine scene and sound direction for rain-soaked streets or warm interiors to craft openers and transitions.

Pro Tips

For complex prompts, organize with the CASTLE schema: core summary, scene, subject, dynamic narrative, audio, and style & color.
Add explicit audio cues such as “Native audio: gentle footsteps and a soft violin melody” to guide the soundtrack.
Specify concrete camera behavior like “slow forward dolly at eye level” to stabilize spatial perspective.
Use 5–8 seconds for a single core action; expand to 10–20 seconds for multi-beat sequences.
Choose auto when you want framing to follow the composition described in the prompt.

Usage notes

FLUX 3 Text to Video is driven by a text prompt, with optional duration, resolution, aspect_ratio, and sound settings.
When sound is true, the result includes dialogue, effects, ambience, or score cues synchronized to on-screen events.
After an API submission, save the returned task_id to query progress and retrieve the final media URL.
Generated clips are delivered as standard video files ready for playback and editing software.

Related Models

FLUX 3 Image to VideoAnimate one start image into 5–20 seconds of video with optional synchronized audio.

FLUX 3 First Last Frame to Video preview

FLUX 3 First Last Frame to VideoInterpolate a coherent transition between required start and end frames.

FLUX 3 Extend VideoContinue an existing MP4 from its final frame for 5–20 new seconds.

FLUX 3 Keyframes to VideoPlace 1–10 keyframes on a 24 fps timeline to direct a multi-shot take.

Gemini Omni 1.1 FlashUse Google Gemini Omni 1.1 Flash for text, frame, reference, and video-edit 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.

FLUX 3 Text to Video API frequently asked questions

What is the FLUX 3 Text to Video API?

FLUX 3 Text to Video is a Black Forest Labs model for generating video from text prompts. It creates 5–20 second high-fidelity clips with physically accurate motion and optional synchronized multi-track native audio at 720p or 1080p. Built on spatiotemporal generation with joint audiovisual modeling, it follows camera and sound design in the prompt while sustaining physical naturalness and shot continuity. You can call it programmatically or try it from the playground above.

How does FLUX 3 Text to Video control synchronized native audio?

With sound set to true by default, the model synthesizes dialogue, foley, ambience, and score cues in sync with the picture. Add audio directions in the prompt to guide the soundtrack; set sound to false when you want silent video only.

How should complex FLUX 3 Text to Video prompts follow the CASTLE principle?

Organize complex shots with the CASTLE six-part schema: core summary, scene, subject, dynamic narrative (camera and timing), audio cues, and style & color. Keep the subject description consistent, use concrete visible verbs for action and camera moves, and state the full arc first so multi-beat continuity stays stable.

How does FLUX 3 Text to Video keep physical stability across 20-second shots?

The model is trained for continuous dynamics including gravity, momentum, cloth, and rigid-body interactions. For near-20-second runs, keep subject trajectories and camera direction consistent in the prompt, and sequence beats in time order to maintain natural physics through the take.

Which aspect ratio should I choose for FLUX 3 Text to Video?

Choose among auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, and 9:16. Use a fixed ratio when the delivery channel is known; with auto, framing follows the composition described in the prompt. Full options are listed in the Parameters section on this page.

When should I use 720p versus 1080p with FLUX 3 Text to Video?

720p costs less per second and suits rapid concept iteration; 1080p delivers finer texture and edge detail for final edits. Both are billed by output seconds, so longer clips cost more—see the Pricing section for the exact credit rates.

How do I direct camera continuity in FLUX 3 Text to Video?

In the dynamic narrative, specify starting framing, move direction, and closing composition—for example, “medium tracking shot at eye level, slow push-in at the end.” A single 5–20 second run fits one continuous camera take or action arc; for longer chained storytelling, continue with the Extend Video or Keyframes endpoints listed under Related Models.