# 1. Transcribe YouTube video directly
omnicaptions transcribe "https://youtube.com/watch?v=VIDEO_ID" -o transcript.md

# 2. Convert to any format
omnicaptions convert transcript.md -o output.srt
omnicaptions convert transcript.md -o output.ass
omnicaptions convert transcript.md -o output.vtt

pip install omni-captions-skills

# Convert (auto-output to same directory, only changes extension)
omnicaptions convert input.srt -t vtt           # → ./input.vtt
omnicaptions convert transcript.md              # → ./transcript.srt

# Specify output file or directory
omnicaptions convert input.srt -o output/       # → output/input.srt
omnicaptions convert input.srt -o output.vtt    # → output.vtt

# Specify format explicitly
omnicaptions convert input.txt -o out.srt -f txt -t srt

omnicaptions convert input.srt -o output.ass --style default    # White text, bottom
omnicaptions convert input.srt -o output.ass --style top        # White text, top
omnicaptions convert input.srt -o output.ass --style bilingual  # White + Yellow (for bilingual)
omnicaptions convert input.srt -o output.ass --style yellow     # Yellow text, bottom

1
00:00:01,000 --> 00:00:03,000
Hello World
你好世界

# Preset: white + yellow
omnicaptions convert bilingual.srt -o output.ass --style bilingual

# Custom colors: green English + yellow Chinese
omnicaptions convert bilingual.srt -o output.ass --line1-color "#00FF00" --line2-color "#FFFF00"

# Mix preset with custom line2 color
omnicaptions convert bilingual.srt -o output.ass --style default --line2-color "#FF6600"

# Auto-detect from .meta.json (saved by download command)
omnicaptions convert abc123.en.srt -o abc123.en.ass --karaoke

# Specify resolution directly
omnicaptions convert input.srt -o output.ass --resolution 4k
omnicaptions convert input.srt -o output.ass --resolution 720p
omnicaptions convert input.srt -o output.ass --resolution 1920x1080

# Detect from video file (uses ffprobe)
omnicaptions convert input.srt -o output.ass --video video.mp4

# Override auto-calculated fontsize
omnicaptions convert input.srt -o output.ass --resolution 4k --fontsize 80

# Basic karaoke (sweep effect - gradual fill)
omnicaptions convert lyrics_LaiCut.json -o lyrics_LaiCut_karaoke.ass --karaoke

# Different effects
omnicaptions convert lyrics_LaiCut.json -o lyrics_LaiCut_karaoke.ass --karaoke sweep    # Gradual fill (default)
omnicaptions convert lyrics_LaiCut.json -o lyrics_LaiCut_karaoke.ass --karaoke instant  # Instant highlight
omnicaptions convert lyrics_LaiCut.json -o lyrics_LaiCut_karaoke.ass --karaoke outline  # Outline then fill

# LRC karaoke (enhanced word timestamps)
omnicaptions convert lyrics_LaiCut.json -o lyrics_LaiCut_karaoke.lrc --karaoke

# 1. Align with LaiCut (get word-level timing in JSON)
omnicaptions LaiCut audio.mp3 lyrics.txt

# 2. Convert to karaoke ASS
omnicaptions convert lyrics_LaiCut.json -o karaoke.ass --karaoke

# Or combine with style
omnicaptions convert lyrics_LaiCut.json -o karaoke.ass --karaoke --style yellow

from omnicaptions import Caption

# Load any format
cap = Caption.read("input.srt")

# Write to any format
cap.write("output.vtt")
cap.write("output.ass")
cap.write("output.ttml")

# Transcribe → Convert → Translate (with Claude)
/omnicaptions:transcribe video.mp4
/omnicaptions:convert video_GeminiUnd.md -o video.srt
/omnicaptions:translate video.srt -l zh --bilingual