puntorigen/avatar-skills / audio-theater
audio-theater
VerifiedTurn a dialogue, a story with dialogue, or a one-line idea into multi-character audio using Gemini TTS, with word-level timecoded transcription (WhisperX or local faster-whisper), realistic ambient/foley SFX (ElevenLabs or the sound-effects skill), and instrumental score/music (MiniMax Music 2.6). Optional stereo spatialization (pan + distance + movement) and an ffmpeg mix with sidechain ducking (music ducks under voices+SFX). Three modes - theater (dramatized radio play), lipsync (clean per-line clips <=15s plus a manifest for the seedance-2 skill), and podcast (two hosts with intro/bed/outro music). With music it delivers three tracks (full mix, music-only, and a no-music stem for animated storyboards) plus a timecoded transcript and per-line voice + SFX/music files. Use for an audio drama, audio theater / audioteatro / radioteatro, a dramatized dialogue, a score for a story/podcast/storyboard, voiceover for lipsync, a TTS conversation, or a podcast episode from a script or idea.
| File | Kind | Size |
|---|---|---|
| REFERENCE.md | markdown | 26.9 KB |
| SKILL.md | skill md | 26.9 KB |
| scripts/_common.py | script | 16.8 KB |
| scripts/audio_music.py | script | 10.3 KB |
| scripts/build_transcript.py | script | 4.8 KB |
| scripts/elevenlabs_sfx.py | script | 3.8 KB |
| scripts/export_lipsync.py | script | 4.4 KB |
| scripts/generate_sfx.py | script | 10.0 KB |
| scripts/generate_voices.py | script | 16.6 KB |
| scripts/mix.py | script | 10.0 KB |
| scripts/mix_spatial.py | script | 23.0 KB |
| scripts/requirements.txt | manifest | 364 B |
| scripts/setup_key.py | script | 4.2 KB |
| scripts/spatial.py | script | 6.8 KB |
| scripts/split_tracks.py | script | 8.3 KB |
| scripts/transcribe.py | script | 8.8 KB |
| scripts/voices.json | config | 2.1 KB |
| scripts/write_script.py | script | 9.9 KB |
scripts/export_lipsync.py
View on GitHub#!/usr/bin/env python3
"""Export lipsync.json from lines.json - a manifest ready for the seedance-2 skill.
Each clean per-line clip becomes a lipsync reference: speaker, voice, exact
transcript, duration, an `ok` flag for the <=15s seedance limit, and a suggested
storyboard panel index. The skill does NOT build the storyboard; this just maps
clips to panels you provide.
Usage:
python3 export_lipsync.py --out audio-theater/ep
python3 export_lipsync.py --lines audio-theater/ep/lines.json --out audio-theater/ep
"""
import argparse
import json
import sys
from pathlib import Path
SCRIPT_DIR = Path(__file__).parent
sys.path.insert(0, str(SCRIPT_DIR))
from _common import ( # noqa: E402
load_config, load_json, save_json, resolve_out_dir,
get_audio_duration, MAX_CLIP_SECONDS,
)
def main():
parser = argparse.ArgumentParser(description="Export seedance-2 lipsync manifest")
parser.add_argument("--out", "-o", required=True, help="Project folder")
parser.add_argument("--lines", default=None, help="Path to lines.json (default <out>/lines.json)")
parser.add_argument("--max-clip-seconds", type=float, default=None,
help="Max clip duration considered OK for seedance (default 15)")
parser.add_argument("--panel-start", type=int, default=1,
help="Panel index to start mapping from (default 1)")
args = parser.parse_args()
config = load_config()
out_dir = resolve_out_dir(args.out)
lines_path = Path(args.lines) if args.lines else out_dir / "lines.json"
if not lines_path.exists():
print(f"Error: {lines_path} not found. Run generate_voices.py first.", file=sys.stderr)
sys.exit(1)
data = load_json(lines_path)
max_clip = args.max_clip_seconds or data.get("max_clip_seconds") \
or config.get("max_clip_seconds", MAX_CLIP_SECONDS)
if data.get("tts_mode") == "two_speaker":
print("Warning: lines.json was made with --two-speaker (single take). Lipsync needs "
"clean per-line clips - re-run generate_voices.py WITHOUT --two-speaker.",
file=sys.stderr)
clips = []
over = []
missing = []
panel = args.panel_start
for ln in data.get("lines", []):
rel = ln.get("file")
duration = ln.get("duration")
if rel:
abs_path = out_dir / rel
if not abs_path.exists():
missing.append(ln["index"])
elif duration is None:
duration = round(get_audio_duration(abs_path), 3)
ok = bool(rel) and duration is not None and duration <= max_clip
if rel and duration is not None and duration > max_clip:
over.append(ln["index"])
clips.append({
"index": ln["index"],
"speaker": ln["speaker"],
"voice": ln.get("voice"),
"transcript": ln.get("text", ""),
"duration": duration,
"file": rel,
"panel": panel,
"ok": ok,
})
panel += 1
manifest = {
"title": data.get("title"),
"language": data.get("language"),
"max_clip_seconds": max_clip,
"clip_count": len(clips),
"all_ok": not over and not missing and all(c["ok"] for c in clips),
"clips": clips,
"seedance_handoff": (
"Per clip: media_upload -> PUT bytes -> media_confirm(type=audio); then "
"generate_video (model seedance_2_0) with a storyboard panel image "
"(reference-image role) + the confirmed audio media_id (audio role). Build "
"the prompt with seedance-2 prompt_tools.py reframe --images 1 --audios 1 "
"--audio-transcript \"<transcript>\". Audio must be <=15s and needs at least "
"one image/video reference."
),
}
out_path = out_dir / "lipsync.json"
save_json(out_path, manifest)
print(f" Clips: {len(clips)} | OK(<= {max_clip}s): {sum(1 for c in clips if c['ok'])}",
file=sys.stderr)
if over:
print(f" Over limit ({max_clip}s): lines {over} - split these lines and re-run.",
file=sys.stderr)
if missing:
print(f" Missing clip files: lines {missing}", file=sys.stderr)
print(json.dumps({
"lipsync_json": str(out_path),
"clip_count": len(clips),
"all_ok": manifest["all_ok"],
"over_limit": over,
"missing": missing,
}, indent=2, ensure_ascii=False))
if __name__ == "__main__":
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |