How to Use Ovi Text to Video in opencode
Ovi Text to Video turns a written scene into a short clip with generated speech, sound effects, and music. Unlike Ovi Image to Video, it creates the starting scene from text alone.
Prompts to try with Ovi Text to Video in opencode
Copy an example into opencode, or ask in your own words.
Use Ovi Text to Video to create a five-second preview of the first greeting in our game's dialogue script. Describe the character and setting from the project notes, choose one short line, wrap it in <S> and <E>, and add quiet room ambience inside <AUDCAP> and <ENDAUDCAP>.
Use Ovi Text to Video to preview a five-second exchange for our tavern scene. The traveler says <S>Any rooms?<E> and the innkeeper replies <S>Just one.<E>. Hold a medium shot and add <AUDCAP>Two distinct voices, faint fireplace crackle.<ENDAUDCAP>.
Use Ovi Text to Video to create a five-second atmosphere study for the harbor level described in our design document. Show waves tapping a wooden pier in one steady shot. Include <AUDCAP>Water lapping against wood, distant gull calls.<ENDAUDCAP>.
Estimate, then generate a 5-second 9:16 clip with Ovi Text to Video: a paper boat drifting down a rainy street. Save the result in ./assets.
Make a 10-second product teaser with Ovi Text to Video for a smartwatch, slow orbit shot, studio lighting.
How to set up Ovi 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 Ovi 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/ovi", "input": { "prompt": "A close-up of someone'\''s face as they pet a cat, their hands stroking the soft fur in the foreground. Their affectionate expression shows as the cat purrs…" } }'
Then paste one of the prompts above: opencode finds Ovi Text to Video on Spiral, shows the price and runs it.
Ovi Text to Video providers and prices
Spiral runs Ovi Text to Video through fal. Open a card for today's price, with every fee included.
resolution: 512x960 $0.26, 512x992 $0.26, 720x720 $0.26, 960x512 $0.26, 992x512 (default) $0.26, 1120x448 $0.26, 448x1120 $0.26 per video.
Settings you can ask for
Ovi 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 | jitter, bad hands, blur, distortion | Negative prompt for video generation. |
| Number of inference steps | 1 to 50 | 30 | The number of inference steps. |
| Seed | a whole number | Random seed for reproducibility. If None, a random seed is chosen. | |
| Resolution | 512x992, 992x512, 960x512, 512x960, 720x720, 448x1120, or 1120x448 | 992x512 | Resolution of the generated video in W:H format. One of (512x992, 992x512, 960x512, 512x960, 720x720, or 448x1120). |
Every API field of Ovi · Text to Video is on its tool page: open its card above.
What can you do with Ovi Text to Video in opencode?
Create short scenes with generated dialogue and sound for game prototypes, character previews, or project presentations. Use project scripts and artwork to prepare focused Ovi scenes for review.
Character introductions
Create a five-second introduction with one short spoken line and a small gesture. Start with a written character description or an existing portrait.
Dialogue rehearsals
Try a brief question and reply before committing to a script. Keep both speakers visible and give each a clearly assigned line.
Product scene concepts
Preview a short product scene with an action and its sound, such as opening a jar or setting down a ceramic cup. Use a written scene or a product image as the starting point.
Game dialogue previews
Test how a short character line works alongside an expression, gesture, and background sound. Use the result to review a scene before producing final game assets.
Atmosphere studies
Explore a rainy street, seaside lookout, or quiet workshop with matching ambient sound. Keep the scene to one shot and compare different sound descriptions.
Short teaching scenes
Illustrate one simple action with a brief spoken cue, such as a barista saying to pour slowly while moving a kettle. Review the generated action before using it in instruction.
More on Ovi Text to Video and opencode
Overview
Ovi Text to Video in other agents
Questions about Ovi Text to Video in opencode
Can opencode use Ovi Text to Video?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Ovi Text to Video like any built-in tool.
How much does Ovi Text to Video cost in opencode?
`resolution`: 512x960 $0.26, 512x992 $0.26, 720x720 $0.26, 960x512 $0.26, 992x512 (default) $0.26, 1120x448 $0.26, 448x1120 $0.26 per video. 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 Ovi Text to Video in opencode?
No. Spiral runs Ovi 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 Ovi Text to Video in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while Ovi Text to Video runs?
Ovi Text to Video runs in the background. opencode starts the run, checks on it and gives you the video when it's ready.
Does Ovi generate sound as well as video?
Yes. Ovi generates picture and sound together, including speech, environmental effects, and background music.
How long are Ovi clips?
Plan scenes for the original Ovi's five-second format at 24 fps. The maker also documents later ten-second checkpoints, so keep scripts for the listed Ovi models short.
How do I tell Ovi what a character should say?
Put the spoken words between <S> and <E>, such as <S>The door is open.<E>. Describe the character's action and expression around that line.
Can Ovi make a conversation between two people?
Yes. Ovi supports multiple speakers and conversational turns. For a five-second scene, try one brief exchange and identify who says each line.
How should I describe background sounds?
For the original Ovi, put ambience, effects, or music between <AUDCAP> and <ENDAUDCAP>. Use concrete sounds such as a cup touching a saucer or rain tapping a window.
Start using Ovi 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


