Files
AutoGPT/autogpt_platform/backend/backend/blocks/video/loop.py
Nicholas Tindle 85b6520710 feat(blocks): Add video editing blocks (#11796)
<!-- Clearly explain the need for these changes: -->
This PR adds general-purpose video editing blocks for the AutoGPT
Platform, enabling automated video production workflows like documentary
creation, marketing videos, tutorial assembly, and content repurposing.

### Changes 🏗️

<!-- Concisely describe all of the changes made in this pull request:
-->

**New blocks added in `backend/blocks/video/`:**
- `VideoDownloadBlock` - Download videos from URLs (YouTube, Vimeo, news
sites, direct links) using yt-dlp
- `VideoClipBlock` - Extract time segments from videos with start/end
time validation
- `VideoConcatBlock` - Merge multiple video clips with optional
transitions (none, crossfade, fade_black)
- `VideoTextOverlayBlock` - Add text overlays/captions with positioning
and timing options
- `VideoNarrationBlock` - Generate AI narration via ElevenLabs and mix
with video audio (replace, mix, or ducking modes)

**Dependencies required:**
- `yt-dlp` - For video downloading
- `moviepy` - For video editing operations

**Implementation details:**
- All blocks follow the SDK pattern with proper error handling and
exception chaining
- Proper resource cleanup in `finally` blocks to prevent memory leaks
- Input validation (e.g., end_time > start_time)
- Test mocks included for CI

### Checklist 📋

#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Blocks follow the SDK pattern with
`BlockSchemaInput`/`BlockSchemaOutput`
  - [x] Resource cleanup is implemented in `finally` blocks
  - [x] Exception chaining is properly implemented
  - [x] Input validation is in place
  - [x] Test mocks are provided for CI environments

#### For configuration changes:
- [ ] `.env.default` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- [ ] I have included a list of my configuration changes in the PR
description (under **Changes**)

N/A - No configuration changes required.


<!-- CURSOR_SUMMARY -->
---

> [!NOTE]
> **Medium Risk**
> Adds new multimedia blocks that invoke ffmpeg/MoviePy and introduces
new external dependencies (plus container packages), which can impact
runtime stability and resource usage; download/overlay blocks are
present but disabled due to sandbox/policy concerns.
> 
> **Overview**
> Adds a new `backend.blocks.video` module with general-purpose video
workflow blocks (download, clip, concat w/ transitions, loop, add-audio,
text overlay, and ElevenLabs-powered narration), including shared
utilities for codec selection, filename cleanup, and an ffmpeg-based
chapter-strip workaround for MoviePy.
> 
> Extends credentials/config to support ElevenLabs
(`ELEVENLABS_API_KEY`, provider enum, system credentials, and cost
config) and adds new dependencies (`elevenlabs`, `yt-dlp`) plus Docker
runtime packages (`ffmpeg`, `imagemagick`).
> 
> Improves file/reference handling end-to-end by embedding MIME types in
`workspace://...#mime` outputs and updating frontend rendering to detect
video vs image from MIME fragments (and broaden supported audio/video
extensions), with optional enhanced output rendering behind a feature
flag in the legacy builder UI.
> 
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
da7a44d794. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->

---------

Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <ntindle@users.noreply.github.com>
Co-authored-by: Otto <otto@agpt.co>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-05 22:22:33 +00:00

116 lines
4.2 KiB
Python

"""LoopVideoBlock - Loop a video to a given duration or number of repeats."""
from typing import Optional
from moviepy.video.fx.Loop import Loop
from moviepy.video.io.VideoFileClip import VideoFileClip
from backend.blocks.video._utils import extract_source_name, strip_chapters_inplace
from backend.data.block import (
Block,
BlockCategory,
BlockOutput,
BlockSchemaInput,
BlockSchemaOutput,
)
from backend.data.execution import ExecutionContext
from backend.data.model import SchemaField
from backend.util.file import MediaFileType, get_exec_file_path, store_media_file
class LoopVideoBlock(Block):
"""Loop (repeat) a video clip until a given duration or number of loops."""
class Input(BlockSchemaInput):
video_in: MediaFileType = SchemaField(
description="The input video (can be a URL, data URI, or local path)."
)
duration: Optional[float] = SchemaField(
description="Target duration (in seconds) to loop the video to. Either duration or n_loops must be provided.",
default=None,
ge=0.0,
le=3600.0, # Max 1 hour to prevent disk exhaustion
)
n_loops: Optional[int] = SchemaField(
description="Number of times to repeat the video. Either n_loops or duration must be provided.",
default=None,
ge=1,
le=10, # Max 10 loops to prevent disk exhaustion
)
class Output(BlockSchemaOutput):
video_out: MediaFileType = SchemaField(
description="Looped video returned either as a relative path or a data URI."
)
def __init__(self):
super().__init__(
id="8bf9eef6-5451-4213-b265-25306446e94b",
description="Block to loop a video to a given duration or number of repeats.",
categories={BlockCategory.MULTIMEDIA},
input_schema=LoopVideoBlock.Input,
output_schema=LoopVideoBlock.Output,
)
async def run(
self,
input_data: Input,
*,
execution_context: ExecutionContext,
**kwargs,
) -> BlockOutput:
assert execution_context.graph_exec_id is not None
assert execution_context.node_exec_id is not None
graph_exec_id = execution_context.graph_exec_id
node_exec_id = execution_context.node_exec_id
# 1) Store the input video locally
local_video_path = await store_media_file(
file=input_data.video_in,
execution_context=execution_context,
return_format="for_local_processing",
)
input_abspath = get_exec_file_path(graph_exec_id, local_video_path)
# 2) Load the clip
strip_chapters_inplace(input_abspath)
clip = None
looped_clip = None
try:
clip = VideoFileClip(input_abspath)
# 3) Apply the loop effect
if input_data.duration:
# Loop until we reach the specified duration
looped_clip = clip.with_effects([Loop(duration=input_data.duration)])
elif input_data.n_loops:
looped_clip = clip.with_effects([Loop(n=input_data.n_loops)])
else:
raise ValueError("Either 'duration' or 'n_loops' must be provided.")
assert isinstance(looped_clip, VideoFileClip)
# 4) Save the looped output
source = extract_source_name(local_video_path)
output_filename = MediaFileType(f"{node_exec_id}_looped_{source}.mp4")
output_abspath = get_exec_file_path(graph_exec_id, output_filename)
looped_clip = looped_clip.with_audio(clip.audio)
looped_clip.write_videofile(
output_abspath, codec="libx264", audio_codec="aac"
)
finally:
if looped_clip:
looped_clip.close()
if clip:
clip.close()
# Return output - for_block_output returns workspace:// if available, else data URI
video_out = await store_media_file(
file=output_filename,
execution_context=execution_context,
return_format="for_block_output",
)
yield "video_out", video_out