Video module
Renders a video from a written script of title cards, images, screen recordings, voiceover and captions.
On this page
What it is for
Renders a video from a written script of title cards, images, screen recordings, voiceover and captions.
- You want a short video built from text, images or a recording of a web page.
- You want to know the cost before rendering.
- A render failed and you want it retried without paying twice for the same speech.
Ask your bot
You do not type commands. Ask in plain words and the bot runs the module for you.
- You ask
- Make a short video that introduces our new opening hours, and tell me the cost before you render it.
- What you get back
- The bot drafts the script, checks it and reports the price estimate before anything is rendered. After rendering, it checks the finished file and shows what each paid step cost.
What the bot does with it
- The bot writes the video script as data from what you ask for. No script is built in.
- It validates the script and gets a price estimate before anything is rendered.
- It renders the video and then runs a check on the finished file.
- Spoken voiceover needs a speech key set for that one run. The key is not stored. Without a voice, voiceover lines appear as captions only.
- It keeps a cost line for each paid step, so you can see what a video cost.
What it stores
Render jobs, cost lines and asset records live in one SQLite file, video/video.sqlite, in the bot's Ambitious folder (/workspace/ambitious by default). The finished video file is written to the output path named in the script.
The module has no screens of its own. It reads JSON, writes JSON, and keeps its data under /workspace/ambitious on the bot's computer. It never sends data anywhere.
Command reference
For the technically curious. You will rarely type these yourself; the bot runs them. Every command answers with the same envelope: whether it worked, which module and command ran, the data, and a list of errors with a hint for each. Open an example to see the command and its output.
ExampleCheck a video script before rendering. The module reports the length in seconds and any problems.
Command
ambitious-video validate --in welcome-video.yaml --jsonOutput
{
"ok": true,
"schemaVersion": 1,
"module": "video",
"command": "validate",
"data": {
"ok": true,
"durationSec": 8,
"problems": []
},
"errors": [],
"meta": { "now": "2026-03-02T09:00:00.000Z", "seed": 7, "version": "0.1.0" }
}ExampleEstimate the cost of the same script with a spoken voice. Only the voiceover step has a price, based on its character count.
Command
ambitious-video estimate --in welcome-video.yaml --jsonOutput
{
"ok": true,
"schemaVersion": 1,
"module": "video",
"command": "estimate",
"data": {
"usd": "0.001800",
"durationSec": 8,
"breakdown": [
{ "step": "title_card", "index": 0, "units": "3", "usd": "0.000000" },
{ "step": "image", "index": 1, "units": "5", "usd": "0.000000" },
{ "step": "voiceover", "index": 2, "units": "120", "usd": "0.001800" }
]
},
"errors": [],
"meta": { "now": "2026-03-02T09:00:00.000Z", "seed": 7, "version": "0.1.0" }
}Show every command
| validate | Checks that a script is usable and reports its length and any problems. |
|---|---|
| plan | Returns the ordered steps and the files the script needs, without rendering. |
| estimate | Returns a price estimate from the built-in price table without calling any outside service. |
| render | Renders the script into a video file, or retries a failed job by its identifier. |
| verify | Checks the length, size, audio and key frames of a rendered video. |
| jobs | Lists the render jobs and their states. |
| ledger | Lists the recorded cost lines. A retry does not add a second line for the same step. |
| selfcheck | Checks the installed file, the database and the video tools it needs, and lists any problems in plain words. |
| commands | Lists every command the module offers. |
Source and releases
The module is open source under the Apache license. Each release carries one bundled file and its checksums; the bot installs it for you.