File size: 4,244 Bytes
1425afc | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 | """
caption_director.py
---------------------------------------
AI Caption Intelligence System
Responsibilities:
- Convert transcript → styled caption segments
- Decide emphasis words
- Break text into readable chunks
- Optimize for TikTok/Reels retention
- Support hook-style captions
INPUT:
words = [
{"word": "hello", "start": 0.2, "end": 0.5},
...
]
OUTPUT:
caption blocks:
[
{
"text": "THIS IS CRAZY",
"start": 0.2,
"end": 2.1,
"style": "hook"
}
]
"""
import re
# -----------------------------
# CONFIG
# -----------------------------
MAX_WORDS_PER_CAPTION = 6
HOOK_KEYWORDS = [
"listen", "wait", "you", "this", "crazy",
"insane", "important", "stop", "secret"
]
# -----------------------------
# UTIL: CLEAN TEXT
# -----------------------------
def clean_word(word):
return re.sub(r"[^a-zA-Z0-9']", "", word).lower()
# -----------------------------
# DETECT EMPHASIS
# -----------------------------
def is_emphasis(word):
w = clean_word(word)
return w in HOOK_KEYWORDS or len(word) > 8
# -----------------------------
# GROUP WORDS INTO CAPTIONS
# -----------------------------
def group_words(words):
captions = []
buffer = []
for w in words:
buffer.append(w)
if len(buffer) >= MAX_WORDS_PER_CAPTION:
captions.append(buffer)
buffer = []
if buffer:
captions.append(buffer)
return captions
# -----------------------------
# BUILD CAPTION BLOCK
# -----------------------------
def build_caption_block(group):
text = []
start = group[0]["start"]
end = group[-1]["end"]
emphasis_count = 0
for w in group:
word = w["word"]
if is_emphasis(word):
text.append(word.upper())
emphasis_count += 1
else:
text.append(word)
caption_text = " ".join(text)
style = "hook" if emphasis_count > 0 else "normal"
return {
"text": caption_text,
"start": start,
"end": end,
"style": style
}
# -----------------------------
# MAIN DIRECTOR
# -----------------------------
def caption_director(words):
"""
Main caption intelligence engine
"""
if not words:
return []
grouped = group_words(words)
captions = []
for group in grouped:
captions.append(build_caption_block(group))
return captions
# -----------------------------
# HOOK CAPTION GENERATOR
# -----------------------------
def generate_hook_caption(words):
"""
Extracts first high-impact caption
"""
for w in words[:20]:
if is_emphasis(w["word"]):
return {
"text": w["word"].upper(),
"start": w["start"],
"end": w["end"],
"style": "hook"
}
return None
# -----------------------------
# AUTO CAPTION PIPELINE
# -----------------------------
def auto_captions(words):
"""
Full pipeline:
- detect hook
- generate captions
"""
captions = caption_director(words)
hook = generate_hook_caption(words)
if hook:
captions.insert(0, hook)
return captions
# -----------------------------
# STYLE DECISION ENGINE
# -----------------------------
def decide_style(caption):
text = caption["text"]
if caption["style"] == "hook":
return "large_bold_center"
if len(text) > 40:
return "small_multi_line"
if text.isupper():
return "emphasis"
return "standard"
# -----------------------------
# EXPORT HELPERS
# -----------------------------
def format_for_render(captions):
"""
Converts captions into render-friendly format
"""
formatted = []
for c in captions:
formatted.append({
"text": c["text"],
"start": c["start"],
"end": c["end"],
"style": decide_style(c)
})
return formatted
# -----------------------------
# PUBLIC API
# -----------------------------
def process_captions(words):
"""
Full external API
"""
captions = auto_captions(words)
return format_for_render(captions) |