FLUX 3 Text to Video: AI Video Generator
Generate cinematic video with native audio using FLUX 3, Black Forest Labs' unified multimodal model. Coming soon on Muapi — get early access now.
Generate cinematic video with native audio using FLUX 3, Black Forest Labs' unified multimodal model. Coming soon on Muapi — get early access now.
About this model
FLUX 3 Text-to-Video is part of Black Forest Labs' newly announced FLUX 3 family, generating cinematic video clips — with optional native, synchronized audio — from a single unified model. FLUX 3 Video shares its core architecture with FLUX 3 Action, Black Forest Labs' action-prediction model for robotics, meaning the same physical-world understanding that predicts robot actions also grounds FLUX 3's video motion in realistic physics. Early testers include Canva, Burda, and Magnific. Muapi is bringing FLUX 3 Text-to-Video online as it exits early access, complementing existing options like Seedance 2 and Veo 3.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapi | TBD at launch | Coming soon — early access via Black Forest Labs, general availability pricing not yet published. |
| Fal.ai | Not available | FLUX 3 is not yet available on Fal.ai. |
| Replicate | Not available | FLUX 3 is not yet available on Replicate. |
Coming soon — early access via Black Forest Labs, general availability pricing not yet published.
FLUX 3 is not yet available on Fal.ai.
FLUX 3 is not yet available on Replicate.
* Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | Text prompt describing the video scene and motion. | A drone shot glides over a bioluminescent forest at night, fireflies drifting between glowing trees, gentle mist rolling across the forest floor, cinematic color grading. |
| Aspect Ratio | Enum (6 options) | Aspect ratio of the output video. | 16:9 |
| Duration | int | Video duration in seconds. | 5 |
| Resolution | Enum (3 options) | Output video resolution. | 720p |
| Generate Audio | boolean | Whether to generate synchronized native audio for the video. | true |
Text prompt describing the video scene and motion.
A drone shot glides over a bioluminescent forest at night, fireflies drifting between glowing trees, gentle mist rolling across the forest floor, cinematic color grading.Aspect ratio of the output video.
16:9Video duration in seconds.
5Output video resolution.
720pWhether to generate synchronized native audio for the video.
trueDeveloper documentation
Write a scene-driven prompt — describe subject, motion, camera movement, and atmosphere.
Configure output — set aspect_ratio, resolution (480p–1080p), and duration (4–10s).
Toggle generate_audio for synchronized native audio.
Submit the request once live:
curl -X POST https://api.muapi.ai/api/v1/flux-3-text-to-video \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt": "A drone shot glides over a bioluminescent forest at night", "aspect_ratio": "16:9", "resolution": "1080p", "duration": 6, "generate_audio": true}'
/api/v1/predictions/{id}/result until completed.Frequently asked
It's Black Forest Labs' newly announced text-to-video mode within the FLUX 3 family, generating cinematic clips with optional native synchronized audio from a single unified multimodal model.
Black Forest Labs opened early access to FLUX 3 Video (alongside FLUX 3 Action) on announcement day. Muapi will enable this endpoint once general API availability opens.
Yes. FLUX 3 Video supports optional native audio generation synchronized to the video, controlled via the `generate_audio` parameter.
Both share the same underlying architecture. FLUX 3 Video is tuned for creative video generation, while FLUX 3 Action extends the same physical-world understanding to action/robotics prediction.
Based on the announcement and comparable models, expect 480p–1080p resolution and roughly 4–10 second clips at launch, with longer durations likely to follow.
Black Forest Labs' early access partners include Canva, Burda, Magnific, Krea, and Picsart, with FLUX-mimic (the video-action model) being tested by Audi and other manufacturing companies.