
BLACKFORESTLABS FLUX 3 Text-to-Video API by Black Forest Labs
Generate a video (with audio) from a text prompt using FLUX 3.
BLACKFORESTLABS FLUX 3 Text-to-Video は Black Forest Labs が開発したモデルです。Atlas Cloud(運営:Atlas Cloud AI LLC)は本モデルへのアクセスを提供するものであり、その所有者ではありません。すべての商標は各所有者に帰属します。
FLUX 3 Text-to-Video
FLUX 3 Text-to-Video generates cinematic videos with synchronized audio directly from a text prompt. Powered by Black Forest Labs' FLUX 3 architecture, it delivers high-fidelity motion, strong prompt adherence, and native audio generation — no post-processing required.
Why Choose This?
-
Native audio generation Produce video and audio together in a single request — dialogue, ambient sound, and music matched to the scene.
-
Explicit duration required Duration must be set explicitly to validate keyframe positions.
-
Auto aspect ratio Use
autoto let the model pick the best fit, or specify any ratio from ultra-wide to portrait. -
High resolution output Generate videos in 720p or 1080p.
-
Adjustable safety Fine-tune the safety tolerance from strict (0) to permissive (4).
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the video to generate |
| aspect_ratio | No | Aspect ratio of the generated video. Default: auto. Options: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16 |
| resolution | No | Video resolution. Default: 720p. Options: 720p, 1080p |
| duration | No | Duration in seconds. Default: 5. Options: 5–20. Cannot be auto — required to validate keyframe positions |
| generate_audio | No | Whether to generate audio. Default: true |
| safety_tolerance | No | Safety level 0 (strictest) to 4 (most permissive). Default: 2 |
| seed | No | Random seed for reproducibility |
How to Use
- Write your prompt — describe the scene, subject, lighting, camera movement, and mood.
- Choose resolution — 1080p for final output, 720p for faster iteration.
- Set aspect ratio — use
autoor pick a ratio to match your target platform. - Set duration — use
autoor specify a value (5–20 seconds). - Run — submit and download your video.
Pricing
Billed per second of generated video, by resolution:
| Resolution | Cost per second |
|---|---|
| 1080p | $0.319 |
| 720p | $0.187 |
Best Use Cases
- Social Media Content — Short-form clips for TikTok, Reels, YouTube Shorts.
- Concept Visualization — Bring ideas to life without filming.
- Marketing Videos — Produce promotional content from text alone.
- Storytelling — Create narrative scenes for creative projects.
Pro Tips
- Be specific about camera movement: "slow dolly forward", "aerial tracking shot", "static wide angle".
- Include lighting and atmosphere: "golden hour", "neon-lit rain", "foggy morning".
- Describe sound in your prompt (e.g. "birdsong", "city ambience") — the model will match audio to it when
generate_audio: true. - Use
seedwhen iterating on prompt wording to isolate the effect of each change.
Notes
promptis the only required field.duration: "auto"andaspect_ratio: "auto"let the model decide; both can be overridden with explicit values.- Generation is asynchronous — submit, then poll for the finished video.
Related Models
- FLUX 3 Image-to-Video — Animate a starting image.
- FLUX 3 First & Last Frame to Video — Interpolate between two images.
- FLUX 3 Keyframes to Video — Pin multiple images to exact frame positions.
- FLUX 3 Extend Video — Continue an existing video clip.


















