Chess Match Montage Generator

pip install videodb

import videodb

# Connect to VideoDB
api_key = "your_api_key"
conn = videodb.connect(api_key=api_key)
coll = conn.get_collection()

from videodb import MediaType

# Upload the chess match video
chess_video = coll.upload(url="https://www.youtube.com/watch?v=dhDe-RcoyAU")

# Upload background music for the montage
bg_music = coll.upload(
    url="https://www.youtube.com/watch?v=S19UcWdOA-I",
    media_type=MediaType.audio
)

from videodb import SceneExtractionType

moves_index_id = chess_video.index_scenes(
    extraction_type=SceneExtractionType.time_based,
    extraction_config={"time": 8, "frame_count": 5},
    prompt="""Look at this chess scene and focus on the chess board. Your task is to detect when pieces are moved.

Respond with ONLY one of these two keywords:
- "Player Moved" — if a chess piece was moved
- "No Move" — if no move occurred (same position, paused, talking, etc.)

Be strict. Only say "Player Moved" if you clearly see a chess piece moved.""",
    name="Chess_Move_Detection"
)

# Get all scenes with descriptions
moves_scenes = chess_video.get_scene_index(moves_index_id)

import json

prompt = f"""Analyze the scene descriptions from this chess video.

Find EVERY scene where the description says "Player Moved".

Return a JSON array containing ONLY the start timestamps (in seconds) of those scenes.

Example output format:
[0, 8, 16, 24, 40, 48]

Rules:
- Return ONLY the JSON array, nothing else
- No descriptions, no explanations, just timestamps

Moves Index : "{moves_scenes}"
"""

response = coll.generate_text(
    prompt=prompt,
    response_type="json",
    model_name="pro"
)

# Parse timestamps from LLM response
timestamps = response["output"]
if isinstance(timestamps, str):
    timestamps = json.loads(timestamps)

from videodb.editor import (
    Timeline, Track, Clip, VideoAsset, AudioAsset,
    Filter, Transition, TextAsset, Font
)

CLIP_DURATION = 5  # seconds per clip
TARGET_CLIPS = 10  # how many clips we want

# Sample timestamps evenly
total_detected = len(timestamps)
step = max(1, total_detected // TARGET_CLIPS)
sampled_timestamps = timestamps[::step][:TARGET_CLIPS]

# Initialize timeline
timeline = Timeline(conn)
timeline.background = "#000000"

# Create intro text
intro_text = TextAsset(
    text="Let the Match Begin",
    font=Font(family="Clear Sans", size=56, color="#FFFFFF"),
)

intro_clip = Clip(
    asset=intro_text,
    duration=3,
    transition=Transition(in_="fade", out="fade", duration=0.5)
)

intro_track = Track()
intro_track.add_clip(0, intro_clip)
timeline.add_track(intro_track)

# Add video clips
video_track = Track()
timeline_position = 3

for i, start_time in enumerate(sampled_timestamps):
    clip = Clip(
        asset=VideoAsset(
            id=chess_video.id,
            start=start_time-1,
            volume=0  # Muting the original audio
        ),
        duration=CLIP_DURATION,
        filter=Filter.contrast,
        transition=Transition(in_="fade", out="fade", duration=1)
    )

    video_track.add_clip(timeline_position, clip)
    timeline_position += CLIP_DURATION

timeline.add_track(video_track)

total_duration = len(sampled_timestamps) * CLIP_DURATION + 3

# Add music track
music_clip = Clip(
    asset=AudioAsset(
        id=bg_music.id,
        start=0,
        volume=0.7
    ),
    duration=total_duration
)

audio_track = Track()
audio_track.add_clip(0, music_clip)
timeline.add_track(audio_track)

# Generate final montage stream
stream_url = timeline.generate_stream()