Spiral gives your agent every tool with one account. Browse the tools →

opencode · VideoReleased 2026-07-17

How to Use FLUX 3 Text to Video in opencode

FLUX 3 Text to Video creates scenes from a written brief, including motion and synchronized sound. Unlike FLUX 3 Image to Video, it builds the opening composition from your description.

Prompts to try with FLUX 3 Text to Video in opencode

Copy an example into opencode, or ask in your own words.

Read the project's creative brief and use FLUX 3 Text to Video to make a 10-second animated scene explaining its main idea. Show one clear action and describe the matching sound effects.

FLUX 3 Text to Videoopencode
Try asking
  • Read the campaign brief and use FLUX 3 Text to Video to make a 15-second concept with three shots: an establishing view, the main action, and a closing detail. Carry one music bed across the cuts.

  • Estimate, then generate a 5-second 9:16 clip with FLUX 3 Text to Video: a paper boat drifting down a rainy street. Save the result in ./assets.

  • Make a 10-second product teaser with FLUX 3 Text to Video for a smartwatch, slow orbit shot, studio lighting.

  • Generate three 5-second b-roll clips of a busy coffee shop with FLUX 3 Text to Video and list what each cost.

How to set up FLUX 3 Text to Video in opencode

Pick the way that suits you. Each takes about two minutes.

Use Spiral's MCP server

  1. Add the server

    Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.

    opencode mcp add spiral --global --url https://api.spiral.ai/mcp
  2. Sign in

    Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.

    opencode mcp auth spiral
  3. Check it

    Spiral shows as connected.

    opencode mcp list

Use the Spiral skill

  1. Send opencode this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. Install and sign in

    Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run FLUX 3 Text to Video

    One request; the result comes back by polling or a webhook.

    curl https://api.spiral.ai/v1/runs \
      -H "Authorization: Bearer $SPIRAL_API_KEY" \
      -H "Content-Type: application/json" \
      -H "Idempotency-Key: $(uuidgen)" \
      -d '{
        "provider": "fal",
        "model": "blackforestlabs/flux-3/text-to-video",
        "input": {
          "prompt": "A red panda walks along a mossy log in a sunlit forest, one continuous unbroken shot. Ambient birdsong and rustling leaves."
        }
      }'

Then paste one of the prompts above: opencode finds FLUX 3 Text to Video on Spiral, shows the price and runs it.

FLUX 3 Text to Video providers and prices

Spiral runs FLUX 3 Text to Video through fal. Open a card for today's price, with every fee included.

falVideo
FLUX 3 Text to Video
blackforestlabs/flux-3/text-to-video

Settings you can ask for

FLUX 3 Text to Video works from your prompt. Ask opencode for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Aspect ratioauto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, or 9:16auto

Aspect ratio of the generated video. auto lets the model choose.

Resolution720p, 1080p, 1440p, or 2160p720p

Resolution of the generated video. 1080p, 1440p (2K) and 2160p (4K) are finished by the video upsampler; exact dimensions depend on the aspect ratio.

Durationauto, 5, 6, 7, 8, 9, 10, 11 and 9 moreauto

Duration of the generated video in seconds. auto lets the model choose.

Generate audioon or offon

Whether to generate audio for the video.

Safety tolerance0 to 42

The safety tolerance level for the generated video. 0 is the strictest and 4 is the most permissive.

Every API field of FLUX 3 Text to Video is on its tool page: open its card above.

What can you do with FLUX 3 Text to Video in opencode?

Create short video assets for a website, app, or game from a project brief. Have the agent turn each visual idea into a concrete shot with action and sound.

Product ad concepts

Create a short product reveal with a clear action and matching sound effects. Use the clip to compare creative directions before planning a shoot.

Animated explainers

Show one idea through a brief animated sequence, such as a seed sprouting or water moving through a landscape.

Storyboard motion studies

Turn a planned scene into a moving shot to assess framing, action, and pacing before production.

Localized presenter clips

Create short on-camera lines in different languages, with a named speaker and exact dialogue. Review pronunciation and speaker attribution before publishing.

Titles within a scene

Build a short sequence around a sign, title, or other typography placed inside the picture.

Stylized social clips

Explore an illustrated or animated look for a short social post, with motion and sound directed around one clear visual idea.

Questions about FLUX 3 Text to Video in opencode

Can opencode use FLUX 3 Text to Video?

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run FLUX 3 Text to Video like any built-in tool.

How much does FLUX 3 Text to Video cost in opencode?

Up to $4.42 per run at the default inputs. `resolution`: 720p (default) $4.42, 1080p $7.54, 1440p $8.32, 2160p $12.22. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.

Do I need a fal account to use FLUX 3 Text to Video in opencode?

No. Spiral runs FLUX 3 Text to Video on its own fal account. You sign in to Spiral once and never paste a key.

How long does it take to set up FLUX 3 Text to Video in opencode?

About two minutes: add the server, then sign in, then check it.

Does opencode wait while FLUX 3 Text to Video runs?

FLUX 3 Text to Video runs in the background. opencode starts the run, checks on it and gives you the video when it's ready.

How long can a FLUX 3 video be?

A clip can run from 5 to 20 seconds, in whole-second increments. Plan longer pieces as separate shots.

Does FLUX 3 generate sound and speech?

Yes. It generates lip-synced speech, sound effects, and ambience alongside the picture, and supports multiple languages and accents.

Can FLUX 3 create several shots in one clip?

Yes. A generation can contain scene changes and different camera angles. Describe the shots in order and make each transition explicit.

Is FLUX 3 limited to realistic footage?

No. You can request animation, motion design, or stylized artistic looks. It can also render typography inside a scene.

How should I prompt dialogue in FLUX 3?

Put the exact spoken words in quotation marks and identify the person speaking on camera. For an off-screen line, explicitly call it a voiceover.

Get started

Start using FLUX 3 Text to Video in opencode

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into opencode:

Set up opencode

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options