File size: 7,938 Bytes
3c9face |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 |
"""
Attribute map utility
---------------------
Expose a structured mapping of the voice design attributes described in
`prompt.txt` together with the inline emotion tags listed in
`emotions.txt`. The module returns data that can be consumed by tooling
to programmatically build descriptions or sweep attribute combinations.
"""
from __future__ import annotations
import json
from pathlib import Path
from typing import Dict, Iterable, List, TypedDict
class AttributeMap(TypedDict, total=False):
metadata: Dict[str, str]
emotions: Dict[str, object]
shared_attributes: Dict[str, Iterable[str]]
realistic_only: Dict[str, object]
creative_only: Dict[str, object]
constraints: Dict[str, object]
defaults: Dict[str, str]
MODULE_DIR = Path(__file__).resolve().parent
EMOTIONS_FILE = MODULE_DIR / "emotions.txt"
PROMPT_FILE = MODULE_DIR / "prompt.txt"
def _load_emotion_tags(path: Path) -> List[str]:
if not path.exists():
raise FileNotFoundError(f"Emotion tag file not found: {path}")
tags: List[str] = []
with path.open("r", encoding="utf-8") as handle:
for raw_line in handle:
line = raw_line.strip()
if not line or line.startswith("#"):
continue
tags.append(line)
return tags
def build_attribute_map(
emotions_path: Path | None = None,
prompt_path: Path | None = None,
) -> AttributeMap:
"""
Return an attribute map that mirrors the guidance in `prompt.txt`.
Parameters
----------
emotions_path:
Optional override for the emotion tag file. Defaults to
`maya1/emotions.txt`.
prompt_path:
Included for symmetry/future validation. Defaults to
`maya1/prompt.txt` and is currently used only for metadata.
"""
emotions_file = emotions_path or EMOTIONS_FILE
prompt_file = prompt_path or PROMPT_FILE
emotion_tags = _load_emotion_tags(emotions_file)
attribute_map: AttributeMap = {
"metadata": {
"source_prompt": str(prompt_file),
"source_emotions": str(emotions_file),
"description": (
"Programmatic representation of Maya voice design attributes. "
"Derived from prompt.txt guidance."
),
},
"emotions": {
"inline_tags": emotion_tags,
"persona_emotion_attribute": [
"neutral",
"energetic",
"excited",
"sad",
"sarcastic",
"dry",
],
"intensity": ["low", "med", "high"],
},
"shared_attributes": {
"age": ["20s", "30s", "40s"],
"gender": ["male", "female"],
"accent": [
"american",
"indian",
"middle_eastern",
"asian_american",
"british",
],
"pitch": ["low", "normal", "high"],
"timbre_realistic": [
"deep",
"warm",
"gravelly",
"smooth",
"raspy",
"nasally",
"throaty",
"harsh",
],
"timbre_creative": [
"deep",
"warm",
"gravelly",
"smooth",
"raspy",
"nasally",
"throaty",
"harsh",
"robotic",
"ethereal",
],
"pacing": [
"very_slow",
"slow",
"conversational",
"brisk",
"fast",
"very_fast",
],
"emotion_intensity": ["low", "med", "high"],
},
"realistic_only": {
"domain": [
"social_content",
"podcast",
"commercial",
"education",
"support",
"entertainment",
"corporate",
"viral_content",
],
"speaking_role": {
"social_content": [
"youtube_vlogger",
"social_media_creator",
"influencer_voice",
"streamer_companion",
],
"podcast": ["podcast_host", "interviewer"],
"commercial": [
"ad_narrator",
"brand_spokesperson",
"product_demo_voice",
"sales_pitch_voice",
],
"education": ["elearning_instructor", "kids_story_voice"],
"support": [
"customer_support_agent",
"virtual_receptionist",
"healthcare_assistant",
],
"entertainment": [
"storyteller",
"social_media_reaction",
"meme_voice",
],
"corporate": [
"explainer_video_voice",
"event_host",
"corporate_training_narrator",
],
"viral_content": ["short_form_narrator", "meme_voice"],
},
"register": ["formal", "neutral", "casual"],
},
"creative_only": {
"character": [
"animated_cartoon",
"ai_machine_voice",
"alien_scifi",
"seductively",
"flirty",
"anime",
"cyborg",
"pirate",
"dark_villain",
"demon",
"gangster",
"mafia",
"dramatic_narrator",
"mythical_godlike_magical",
"spy",
"vampire",
"alpha",
],
},
"constraints": {
"pitch": {
"note": (
"For age 40s, avoid high pitch (use sparingly, <= 15% of uses)."
)
},
"creative_timbre": {
"robotic": [
"ai_machine_voice",
"cyborg",
"alien_scifi",
"mythical_godlike_magical",
],
"ethereal": [
"ai_machine_voice",
"cyborg",
"alien_scifi",
"mythical_godlike_magical",
],
},
"character_pacing_overrides": {
"mafia": ["slow", "conversational"],
"flirty": ["slow", "conversational"],
"alpha": ["fast", "very_fast"],
"seductively": ["very_slow", "slow"],
},
"defaults": "Default persona emotion should be neutral unless specified.",
},
"defaults": {
"age": "20s",
"gender": "female",
"accent": "american",
"pitch": "high",
"timbre": "warm",
"pacing": "brisk",
"emotion": "excited",
"emotion_intensity": "med",
"domain": "social_content",
"speaking_role": "influencer_voice",
"register": "casual",
},
}
return attribute_map
def main() -> None:
"""
CLI helper: print the attribute map as JSON for inspection.
"""
attribute_map = build_attribute_map()
print(json.dumps(attribute_map, indent=2, sort_keys=True))
if __name__ == "__main__":
main()
|