# FLUX 3 > Create 5–20s FLUX 3 videos from text or one still with native audio. Choose 720p or 1080p, see credits from 150 first, and keep clips private on MixVio. - [Canonical FLUX 3 page](https://mixvio.ai/models/flux-3) - [Official model source](https://bfl.ai/models/flux-3) ## Route summary - **Provider:** Black Forest Labs - **Media:** video - **Inputs:** Text · Image - **Output:** 720p–1080p video + audio - **Duration:** 5–20s - **Native audio:** Yes - **Credits:** 150–1,020 credits - **Availability:** Available ## Capabilities - **Native dialogue and mix:** Speech, room tone, and effects generate with the picture. Name who speaks and the room so you can review lip sync and the mix before you publish. - **Multiple shots in one take:** Switch scenes and camera angles inside one 5–20 second generation. Cover setup, a turn, and a finish instead of a single frozen moment. - **Text or still to video:** Start from a written brief or one owned still. Image-to-video uses that frame as the opening picture; the prompt describes how the clip unfolds. - **In-scene typography:** Signs, terminals, and titles can sit in the picture instead of as a separate overlay. Spell the exact words you need, then review them before you publish. ## How to use 1. **Start from text or a still:** Use text-to-video for a new scene, or add one owned start frame for image-to-video. Prefill from a demo if you want—nothing runs until you generate. 2. **Direct motion, camera, and sound:** Write subject, action, setting, camera, and sound. Name who speaks and spell any on-screen words. For a longer take, cover setup, turn, and finish. 3. **Generate, review, then iterate:** Select 5–20 seconds and 720p or 1080p, confirm the credit estimate, then generate. Review identity, readable text, dialogue, and lip sync before publishing or iterating. ## Pricing From 150 credits per 5-second 720p clip, up to 1,020 for 20 seconds at 1080p. Duration and resolution change the quote. Confirm the exact reservation before you generate. - [MixVio pricing](https://mixvio.ai/pricing) ## FAQ ### What is FLUX 3? FLUX 3 is Black Forest Labs’ multimodal model. On MixVio the public family is FLUX 3 Video: one private 5–20 second clip per run from text or one owned still, with native audio at 720p or 1080p. [FLUX 3 model page](https://bfl.ai/models/flux-3) ### What can I generate with FLUX 3 on MixVio? Use text-to-video for a new scene, or image-to-video with one owned PNG, JPEG, or WebP start frame. Each run returns one private clip with native audio. ### Does FLUX 3 generate native audio? Yes. Public FLUX 3 routes return video with native audio in the same pass, including dialogue, effects, and ambience when you describe them. Official BFL pricing includes audio at no extra charge. Review speech, mix, and lip sync before publishing. [FLUX 3 FAQ](https://bfl.ai/models/flux-3) ### Can FLUX 3 do speech and on-screen text? Yes—describe who speaks and spell any on-screen words in the prompt. Public routes return native audio in the same pass. Review dialogue, lip sync, and readable type before you publish; MixVio does not guarantee perfect spelling or sync. [FLUX 3 model page](https://bfl.ai/models/flux-3) ### Which durations, resolutions, and ratios are supported? Each run is 5–20 whole seconds at 720p or 1080p. Text-to-video and image-to-video both support Auto, 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16. MixVio does not publish 4K, auto duration, or a 2:1 ratio on this family. ### How many credits does FLUX 3 use? FLUX 3 is not available on the Free plan. Paid plans reserve from 150 credits. Typical anchors: 150 credits for 5 seconds at 720p, 300 for 10 seconds at 720p, and 1,020 for 20 seconds at 1080p. Duration and resolution change the quote. The generator shows the exact reservation before you submit. Failed runs cost no credits. ### Is FLUX 3 free? No. Video generation is not included on the Free plan. Paid plans quote credits from duration and resolution before you submit. Failed runs cost no credits. ### How does FLUX 3 compare with Seedance 2.5, Kling 3.0, and MiniMax H3? Stay on FLUX 3 for a 5–20 second clip with native audio from text or one still at 720p or 1080p. Switch to Seedance 2.5 for 4–30 second one-takes and packs up to 50 files, Kling 3.0 for 5/10/15 second cinematic shots with an optional end frame, or MiniMax H3 for 4–15 second multimodal packs at 768p or 2K. ### Is this the same as FLUX 2 Max? No. FLUX 2 Max is a separate image route. FLUX 3 on MixVio is video only, with different endpoints, durations, and credits. ### Is Draft, keyframes, or video extend available on MixVio? Not on the public MixVio routes. This page ships text-to-video and image-to-video only. Draft, first-and-last-frame, timestamped keyframes, video continuation, and FLUX 3 Image stay Pending until the generator exposes matching controls. ### Can I use FLUX 3 videos commercially? Paid MixVio generations can be used commercially, subject to the Terms of Service and current Black Forest Labs / serving provider terms, when you have rights to every prompt, reference, likeness, brand asset, voice, and sound direction. Completed outputs are archived privately to your MixVio workspace. Review identity, readable text, logos, dialogue, and lip sync before publishing. MixVio does not guarantee exclusivity or trademark clearance. ### Can I use real faces or celebrity likenesses? Only use faces, voices, and likenesses you own or are authorized to use. Public figures, deceptive impersonation, deepfake-style face swaps, minors, and other prohibited content can be blocked by MixVio moderation or Provider safety checks. When a request is allowed, still review identity and consent before any commercial or public use.