Menu
Align text to audio timestamps using Qwen3-ForcedAligner (~30ms precision)
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | Caption Alignment |
| description | Align text to audio timestamps using Qwen3-ForcedAligner (~30ms precision) |
| triggers | ["Karaoke captions","Word-level timestamps","Subtitle synchronization"] |
Align text to audio timestamps for karaoke-style rolling captions.
from skills.align_captions import CaptionAligner
aligner = CaptionAligner()
# Single audio file
captions = await aligner.align_audio(
audio_path=Path("speech.wav"),
text="Hello world!",
language="English",
)
# Returns list of AlignedCaption with word-level timing
# Multi-file dialogue
captions = await aligner.align_dialogue_lines(
audio_paths=[Path("line1.wav"), Path("line2.wav")],
texts=["Hello!", "Hi there!"],
)
@dataclass
class WordSegment:
text: str
start_ms: int
end_ms: int
@dataclass
class AlignedCaption:
text: str # Phrase text
start_ms: int # Phrase start
end_ms: int # Phrase end
words: list[WordSegment] # Word-level timing for karaoke
pip install qwen-asr jieba torch
Full pipeline from manga panels to animated video. Two audio modes: dialogue (Qwen3-TTS + karaoke captions) or music (ElevenLabs + rolling lyrics).
Burn karaoke captions into video using FFmpeg ASS subtitles (~20s for 16s video)
Generate multi-panel manga from character reference and story beats
Generates original background music using Google's Music Generation API. Creates soundtracks matched to scene mood and timing.
Concatenates video clips and optionally adds background music using FFmpeg.
Generates anime character images from photo analysis using Nano Banana Pro (gemini-3-pro-image-preview). Creates character sheets with full body and portrait views at 2K resolution.