How to Use Kandinsky 6.0 Pro Text to Video in opencode
Kandinsky 6.0 Pro Text to Video creates five-second scenes with synchronized sound from a written description. Unlike Kandinsky 6.0 Pro Image to Video, it lets you invent the starting composition without a reference image.
Prompts to try with Kandinsky 6.0 Pro Text to Video in opencode
Copy an example into opencode, or ask in your own words.
Read the project's creative brief and use Kandinsky 6.0 Pro Text to Video to make a five-second opening shot: a paper boat moves across a puddle, the camera slowly follows, and light rain supplies the sound. Save it with the project's draft media.
Use Kandinsky 6.0 Pro Text to Video to create a five-second forest cutaway for the project: leaves move in a breeze, the camera stays still, and birds call in the distance. Add the clip to the media preview.
Use Kandinsky 6.0 Pro Text to Video to generate a five-second scene of a fictional shopkeeper turning toward the camera and saying 'Welcome back.' Include soft shop ambience, then add the result to the project's storyboard preview.
Estimate, then generate a 5-second 9:16 clip with Kandinsky 6.0 Pro Text to Video: a paper boat drifting down a rainy street. Save the result in ./assets.
Make a 10-second product teaser with Kandinsky 6.0 Pro Text to Video for a smartwatch, slow orbit shot, studio lighting.
How to set up Kandinsky 6.0 Pro Text to Video in opencode
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- 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
- 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
- Check it
Spiral shows as connected.
opencode mcp list
Use the Spiral skill
- Send opencode this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- 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
- Create an API key
In the console, under API keys.
- Run Kandinsky 6.0 Pro 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": "fal-ai/kandinsky6-pro/text-to-video", "input": { "prompt": "A cat and a dog baking a cake together in a kitchen. The cat whisks batter while the dog sniffs the flour; a kitchen timer ticks and a mixer hums in the…" } }'
Then paste one of the prompts above: opencode finds Kandinsky 6.0 Pro Text to Video on Spiral, shows the price and runs it.
Kandinsky 6.0 Pro Text to Video providers and prices
Spiral runs Kandinsky 6.0 Pro Text to Video through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Kandinsky 6.0 Pro Text to Video works from your prompt. Ask opencode for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Negative prompt | what to leave out, in words | What to avoid in the video. Defaults to the model's built-in negative prompt. | |
| Aspect ratio | 16:9, 9:16, 1:1, 4:3, or 3:4 | 16:9 | The aspect ratio of the generated video. |
| Generate audio | on or off | on | Whether to generate a synchronized audio track. |
| Enable prompt expansion | on or off | off | Whether to rewrite the prompt into a detailed video+audio description with the model's own Qwen2.5-VL text encoder before generating. |
| Upscale factor | 2, 2.25, or 4 | If set, upscale the generated video by this factor with Kandinsky 6 video super-resolution. One of 2, 2.25 or 4; 2.25 turns the 480p output into 1080p. | |
| Seed | a whole number | The random seed used for the generation process. | |
| Number of inference steps | 8 to 50 | 50 | The number of denoising steps. |
| Guidance scale | 1 to 10 | 5 | Classifier-free guidance strength. |
Every API field of Kandinsky 6.0 Pro · Text to Video is on its tool page: open its card above.
What can you do with Kandinsky 6.0 Pro Text to Video in opencode?
Create five-second video assets with synchronized sound for a project's visual drafts. A coding agent can use the project's creative brief to specify action, camera movement, and audio, then place the result in a preview.
Product scene drafts
Draft a five-second shot of a ceramic mug as steam rises and the camera moves closer. Describe a quiet room and a faint cup clink for the soundtrack.
Film shot previews
Preview one camera move and one action before production, such as a slow pullback as a character opens a door. Include the door sound and room ambience.
Short character dialogue
Create a five-second character greeting with a brief spoken line. Check the words and mouth movement before placing it in an edit.
Atmospheric cutaways
Make a short rain, forest, or seaside cutaway with matching environmental sound for a video draft.
Sound and action studies
Test a visible event and its sound together, such as coins sliding across a table or a book closing. Keep the scene focused on that event.
English and Russian creative drafts
Draft short scenes from English or Russian descriptions. Use them to compare how a creative brief translates into action, camera movement, and sound.
Scenes invented from a brief
Turn a written idea into a five-second scene when no starting image exists. Specify the composition, action, camera move, and soundtrack together.
More on Kandinsky 6.0 Pro Text to Video and opencode
Overview
Kandinsky 6.0 Pro Text to Video in other agents
Questions about Kandinsky 6.0 Pro Text to Video in opencode
Can opencode use Kandinsky 6.0 Pro Text to Video?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Kandinsky 6.0 Pro Text to Video like any built-in tool.
How much does Kandinsky 6.0 Pro Text to Video cost in opencode?
Up to $2.482974 per run at the default inputs. 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 Kandinsky 6.0 Pro Text to Video in opencode?
No. Spiral runs Kandinsky 6.0 Pro 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 Kandinsky 6.0 Pro Text to Video in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while Kandinsky 6.0 Pro Text to Video runs?
Kandinsky 6.0 Pro 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 are Kandinsky 6.0 Pro videos?
Kandinsky 6.0 Pro generates five-second clips. Plan a brief action or exchange for each clip; assemble longer sequences in an editor.
Does Kandinsky 6.0 Pro generate sound and speech?
Yes. It generates synchronized 44 kHz audio and supports speech with lip-sync. Describe the sounds you want, and keep spoken lines short enough for five seconds.
Is Kandinsky 6.0 Pro output native Full HD?
Full HD comes from super-resolution. The documented landscape base clip is 864 by 480 pixels, with 2.25-times upscaling used for Full HD.
Can I prompt Kandinsky 6.0 Pro in Russian?
Yes. Kandinsky 6.0 Pro supports English and Russian prompts.
What should a Kandinsky 6.0 Pro prompt include?
Describe the subject, action, setting, camera movement, and sound. The maker's examples pair a visual description with explicit audio direction; prompt expansion can flesh out a short description.
Start using Kandinsky 6.0 Pro 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 https://spiral.ai/SKILL.md


