> Version notice: This site documents BAML v0, the legacy DSL. BAML v1 is a separate, fully featured programming language in public beta. If the user intends to use BAML v1, ignore this site's content and use the BAML v1 documentation instead. If the intended version is unclear, clarify it before using this page.
> For clean Markdown of any page, append .md to the page URL. For the complete documentation index, see https://docs.boundaryml.com/llms.txt. For MCP access, connect to https://docs.boundaryml.com/_mcp/server.
# Video
> Learn how to handle video inputs in BAML functions
Video values to BAML functions can be created in client libraries. This document explains how to use these functions both at compile time and runtime to handle video data. For more details, refer to [video types](/ref/baml/types#video).
> **Info**
>
> When you create a `Video` using `from_url` (Python) or `fromUrl` (TypeScript), the URL is passed directly to the model without any intermediate fetching. If the model cannot access external media, it will fail on such inputs. In these cases, convert the video to Base64 before passing it to the model.
>
> For AWS Bedrock models with video support, you can pass `s3://` URIs through `Video.from_url`. BAML forwards the URI as an `s3Location` and includes the `media_type` you provide so Bedrock can fetch the object without uploading it through BAML first. BAML does **not** infer video MIME types for Bedrock requests, so always supply the correct `media_type` (for example, `video/mp4`).
> **Warning**
>
> Direct video inputs are only supported by Google Gemini, Google Vertex AI, and AWS Bedrock models that advertise video support. Other providers (Anthropic Claude, OpenAI GPT-4o) will error or require you to extract frames as images or provide transcripts. See the model compatibility table below for details.
## Usage Examples
```python
from baml_py import Video
from baml_client import b
async def test_video_input():
# Create a Video object from a URL
video = Video.from_url("https://www.youtube.com/watch?v=dQw4w9WgXcQ")
res = await b.TestVideoInput(video=video)
# Create a Video object from Base64 data
video_b64 = "AAAAGGZ0eXBpc29t..."
video = Video.from_base64("video/mp4", video_b64)
res = await b.TestVideoInput(video=video)
# Pass an S3 video reference directly to an AWS Bedrock model
bedrock_video = Video.from_url(
"s3://baml-test-bucket/example/path/video.mp4", media_type="video/mp4"
)
res = await b.TestAwsVideoDescribe(video_input=bedrock_video)
```
```typescript
import { b } from '../baml_client'
import { Video } from "@boundaryml/baml"
// Create a Video object from a URL
let res = await b.TestVideoInput(
Video.fromUrl('https://www.youtube.com/watch?v=dQw4w9WgXcQ')
)
// Create a Video object from Base64 data
const video_b64 = "AAAAGGZ0eXBpc29t..."
res = await b.TestVideoInput(
Video.fromBase64('video/mp4', video_b64)
)
// Pass an S3 video reference directly to an AWS Bedrock model
const bedrockVideo = Video.fromUrl(
's3://baml-test-bucket/example/path/video.mp4',
'video/mp4',
)
// Pass `bedrockVideo` to any function backed by a Bedrock model with video support
// Browser-specific methods
const fileVideo = await Video.fromFile(file)
const blobVideo = await Video.fromBlob(blob, 'video/mp4')
const fetchedVideo = await Video.fromUrlToBase64('https://www.youtube.com/watch?v=dQw4w9WgXcQ')
```
```tsx
import { useTestVideoInput } from '../baml_client/react/hooks'
import { Video } from "../baml_client/react/media"
export function TestVideoInput() {
const { mutate } = useTestVideoInput()
const handleClick = async () => {
const video = await Video.fromUrl('https://www.youtube.com/watch?v=dQw4w9WgXcQ')
mutate(video)
}
return (
)
}
```
**`Rust`**
```rust Rust
use myproject::baml_client::sync_client::B;
use myproject::baml_client::new_video_from_url;
fn test_video_input() {
// Create a Video from a URL
let video = new_video_from_url("https://example.com/sample.mp4", None);
let res = B.TestVideoInput.call(&video).unwrap();
}
```
```ruby
# Ruby implementation is in development.
```
## API Reference
#### Python
### Static Methods
**`from_url`** `(url: str, media_type: Optional[str] = None) -> Video`
Creates a Video object from a URL. Optionally specify the media type, otherwise it will be inferred from the URL. When targeting AWS Bedrock with an `s3://` URI, pass the media type explicitly so the request includes the expected `format`.
---
**`from_base64`** `(media_type: str, base64: str) -> Video`
Creates a Video object using Base64 encoded data along with the given MIME type.
---
### Instance Methods
**`is_url`** `() -> bool`
Check if the video is stored as a URL.
---
**`as_url`** `() -> str`
Get the URL of the video if it's stored as a URL. Raises an exception if the video is not stored as a URL.
---
**`as_base64`** `() -> list[str]`
Get the base64 data and media type if the video is stored as base64. Returns `[base64_data, media_type]`. Raises an exception if the video is not stored as base64.
---
**`baml_serialize`** `() -> dict`
Convert the video to a dictionary representation. Returns either `{"url": str}` or `{"base64": str, "media_type": str}`.
---
#### TypeScript
### Static Methods
**`fromUrl`** `(url: string, mediaType?: string) => Video`
Creates a Video object from a URL. Optionally specify the media type, otherwise it will be inferred from the URL. When targeting AWS Bedrock with an `s3://` URI, pass the media type explicitly so the request includes the expected `format`.
---
**`fromBase64`** `(mediaType: string, base64: string) => Video`
Creates a Video object using Base64 encoded data along with the given MIME type.
---
**`fromFile`** `(file: File) => Promise