Black Forest Labs Flux 3 Text To Video

Black Forest Labs Flux 3 Text To Video

Playground

FLUX 3 Text-to-Video generates cinematic 5-20 second videos from text prompts, with coherent motion, cinematic composition, optional synchronized audio, and 720P / 1080P output for creative videos, social content, ads, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

FLUX 3 Text-to-Video turns a written prompt into a short video with coherent motion, cinematic composition, and optional synchronized audio. Describe the subject, action, environment, camera movement, pacing, and sound to create a ready-to-use clip without an input image.

Key Capabilities

• Generate 5-20 second videos directly from text prompts.
• Control subject behavior, scene details, camera movement, lighting, pacing, and visual style.
• Generate optional synchronized audio for ambience, sound effects, and other scene-aware sounds.
• Choose 720p or 1080p output for previews, social content, advertisements, and production drafts.
• Use landscape, portrait, square, or cinematic aspect ratios for different publishing formats.

Parameters

How to Use

1. Write a complete prompt describing what happens, who or what appears, where the scene takes place, and how the camera should move.
2. Choose an aspect ratio that matches the destination, such as 9:16 for vertical short-form video or 16:9 for landscape content.
3. Select the output resolution and set a duration from 5 to 20 seconds.
4. Keep generate_audio enabled when the scene benefits from ambient sound, sound effects, music, or dialogue.
5. Submit the request and download the generated video after processing is complete.

Prompting Tips

• Start with the main subject and the most important action, then add the environment, lighting, mood, and camera direction.
• Use explicit motion verbs such as walk, turn, lift, pour, run, orbit, track, zoom, or tilt.
• Describe timing when the action has multiple beats, such as a subject pausing, looking toward the camera, and then moving into the foreground.
• Mention sounds that should match the scene, including footsteps, rain, traffic, room tone, music, or dialogue.

Pricing

Pricing is calculated by billed video duration and output resolution.

Billing Rules

• The billed duration is rounded up to the next whole second.
• The minimum billed duration is 5 seconds.
• The maximum billed duration is 20 seconds.
• Audio generation does not add a separate charge in the current pricing formula.
• Example: a 10-second 720p video costs $1.70.
• Example: a 10-second 1080p video costs $2.90.

Best Use Cases

• Short-form social videos for vertical, square, and landscape platforms.
• Product demonstrations, advertisements, and branded motion creatives.
• Cinematic concept clips, storyboards, and pre-visualization.
• Character action tests, mood films, and promotional trailers.

Notes

• This model generates video from text prompts and does not require an input image.
• Clear descriptions of motion and camera direction generally produce more controllable results.
• Generated audio is intended to match the scene and may vary with the prompt and visual action.

Related Models

• FLUX 3 Start-End-to-Video — Generate video using both a starting frame and an ending frame.
• FLUX 3 Image-to-Video — Animate a reference image into a video.
• FLUX 3 Video Extend — Extend an existing video with new generated footage.
• FLUX 3 Text-to-Video — Generate video directly from a text prompt.

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'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "9:16",
  "resolution": "720p",
  "duration": 5,
  "generate_audio": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/black-forest-labs/flux-3/text-to-video" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 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) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters