Public API v1

Create videos programmatically

One endpoint, four workflows. Send a prompt, an idea, a script or an article URL, and Veedio writes the scenes, generates a visual for each one, narrates them, burns word-timed captions, ducks a music bed under the voice and renders the file. A generation costs 3 credits plus a charge per scene that follows what fills it: 2 for a still or stock footage, 13 for a scene the video model sets in motion. A 5-scene short is 13 credits with stills and 68 animated. You can get that quote for free before you spend anything.

Full API reference Create an API key

What are you starting from?

The workflow field decides what source must contain and how much of the writing we do. Everything else is optional and has a default.

Words you already have

Script to video
Your script, narrated close to verbatim. You control every sentence.
script-to-video

Something for us to write from

Quick start

Your first video in three steps

1Create a key

Settings → API keys. The plaintext is shown once and only its hash is stored, so a lost key is minted again rather than recovered. It looks like vd_live_….

Header

Authorization: Bearer vd_live_...

# also accepted
x-api-key: vd_live_...
x-veedio-api-key: vd_live_...
key: vd_live_...

2Start a generation

202 Accepted comes back with an id, the credit deposit and a link to the video's page. The video itself does not exist yet.

cURL

curl -X POST https://www.veedio.co/api/v1/videos \
  -H "Authorization: Bearer $VEEDIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "workflow": "prompt-to-video",
  "source": {
    "text": "A 30-second video about why the ocean is salty, fun and educational"
  }
}'

JavaScript

const res = await fetch("https://www.veedio.co/api/v1/videos", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.VEEDIO_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "workflow": "prompt-to-video",
    "source": {
      "text": "A 30-second video about why the ocean is salty, fun and educational"
    }
  }),
});

const video = await res.json();
console.log(video.id, video.status);

Python

import os
import requests

res = requests.post(
    "https://www.veedio.co/api/v1/videos",
    headers={"Authorization": f"Bearer {os.environ['VEEDIO_API_KEY']}"},
    json={
        "workflow": "prompt-to-video",
        "source": {
            "text": "A 30-second video about why the ocean is salty, fun and educational",
        },
    },
    timeout=30,
)

video = res.json()
print(video["id"], video["status"])

3Get the result

Generation is asynchronous and takes a few minutes. Poll until status is ready or failed; videoUrl is the finished MP4, and scenes[] fills in as it goes, so you can show progress rather than a spinner.

cURL

curl https://www.veedio.co/api/v1/videos/8f1c0f2e-... \
  -H "Authorization: Bearer $VEEDIO_API_KEY"

Poll no more than once every few seconds. There is no completion webhook yet — it is the next thing planned for this surface, and until then polling is the whole story.
Quote before you spend: POST /api/v1/credits/estimate takes the same body as the create call and ignores the fields it does not use.

All four workflows at a glance

What each one needs, and what you can set on top of it. Every optional field has a default, so the minimal request is two lines.

Prompt to video

prompt-to-video

A brief. We write the script, generate the visuals and cut it.

requires source.text

Script to video

script-to-video

Your script, narrated close to verbatim. You control every sentence.

requires source.text

Idea to video

idea-to-video

A bare idea, expanded into an angle and then a script.

requires source.text

Article to video

article-to-video

A link, read and turned into a short: an article, a video, a post, a thread or a PDF.

requires source.url

Required input and available options for each workflow
Workflow	Requires	source	voice	captions	music	style	ratio
Prompt to video	source.text	required	available	available	available	available	available
Script to video	source.text	required	available	available	available	available	available
Idea to video	source.text	required	available	available	available	available	available
Article to video	source.url	required	available	available	available	available	available

● required · ✓ available with a default

Send nothing but a source and you get:voice: rachelcaptions: bold-centermusic: upliftingstyle: cinematicratio: 9:16

Before you build

What this API cannot do

Stated plainly, because finding out at integration time wastes a day.

No file uploads over the API. It takes text and URLs, not bytes — so no captioning footage you already have and no podcast repurposing. Links go further than that sounds: photoUrl makes a hosted image the opening frame, and a url source pointing at a PDF is read as a document, so photo-to-video and PDF-to-video work when the file is reachable. The app's own uploader turns a local JPEG, PNG, WebP or PDF into exactly that kind of link.
No face swap and no voice cloning. A presenter avatar lip-syncing the script is a Pro and Studio feature, not a gap.
Three minutes is the ceiling. targetSeconds is 30, 60, 90 or 180 — free accounts up to 60, paid plans to 180. There is no long-form mode past that.
29 languages, spoken by the same five voices. Image prompts and stock searches stay in English whichever you pick, because the image models read English.
No 4K. Output is 1080-class, and there are four caption styles, all burned in — no subtitle file to download and no custom font.
Every frame is generated, or licensed stock where the deployment has a Pexels key. No gameplay library, and no character kept consistent across scenes.
No webhooks yet. Poll GET /api/v1/videos/{id}; a completion callback is the next thing planned for this surface.
No scheduling through the API yet. Auto-Mode schedules are created in the app.

Create videos programmatically

What are you starting from?

Words you already have

Script to video

Something for us to write from

Prompt to video

Idea to video

Article to video

Your first video in three steps

All four workflows at a glance

What this API cannot do

More resources

Full API reference

MCP server

CLI

Agent skills

Docs for LLMs

Master FAQ