Files
voice_copy/voice-changer/app/voice_changer.py
EJClaw b0460fdff7 Add Windows realtime voice changer (RVC via Applio) + set operator to 사금향
- voice-changer/: install.bat (uv + Python 3.12 + pinned Applio + torch cu128),
  VoiceChanger.exe launcher (mingw), tkinter GUI (model list, auto ±12 pitch
  across genders, mic/output/monitor devices, latency, noise gate),
  train.bat (preprocess/extract/train/index → models/<id>), examples.bat
  (Korean example models from KSS + Zeroth-Korean), build-release.sh
- consent-recorder: default OPERATOR_NAME=사금향

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 14:34:03 +09:00

314 lines
14 KiB
Python

"""실시간 음성 변환기 (Windows 게임PC 용 화면).
마이크로 들어온 내 말소리를 고른 목소리 모델로 바꿔서 출력 장치로 내보낸다.
디스코드 · 게임에 쓰려면 출력을 가상 케이블(VB-CABLE 의 "CABLE Input")로 두고,
디스코드 입력 장치를 "CABLE Output" 으로 고른다.
"""
import multiprocessing as mp
import queue
import sys
import threading
import time
import tkinter as tk
from tkinter import messagebox, ttk
from common import SETTINGS, load_json, save_json, use_engine
from models import GENDERS, auto_pitch, list_models
LATENCY = {"낮음 (약 0.15초, GPU 여유 필요)": 128, "보통 (약 0.25초)": 250, "안정 (약 0.4초)": 400}
def list_devices():
"""(입력 이름→번호, 출력 이름→번호). 가상 케이블을 출력 맨 앞에 둔다."""
from rvc.realtime.audio import list_audio_device
ins, outs = list_audio_device()
def is_virtual(d):
n = d.name.lower()
return "cable" in n or "virtual" in n or "vb-audio" in n
outs = sorted(outs, key=lambda d: not is_virtual(d))
ins = sorted(ins, key=is_virtual) # 마이크를 앞에, 가상 케이블은 뒤에
fmt = lambda d: f"{d.name} ({d.host_api})"
return {fmt(d): d.index for d in ins}, {fmt(d): d.index for d in outs}
class Converter:
"""Applio 실시간 엔진(AudioCallbacks) 하나를 켜고 끈다."""
def __init__(self):
self.callbacks = None
@property
def running(self):
return self.callbacks is not None
def start(self, model, pitch, in_id, out_id, monitor_id, chunk_ms, threshold, index_rate, on_status):
from rvc.realtime.audio import resolve_sample_rate
from rvc.realtime.callbacks import AudioCallbacks
sr = resolve_sample_rate(in_id, False, 48000)
block = int(chunk_ms * sr / 1000)
cb = AudioCallbacks(
block_frame=block,
cross_fade_overlap_size=0.05,
extra_convert_size=2.5,
model_path=str(model.pth),
index_path=str(model.index) if model.index else "",
f0_method="rmvpe",
embedder_model="contentvec",
silent_threshold=threshold,
f0_up_key=pitch,
index_rate=index_rate if model.index else 0.0,
protect=0.33,
volume_envelope=1.0,
monitor=monitor_id is not None,
audio_sample_rate=sr,
)
self.callbacks = cb
try:
cb.audio.start(
input_device_id=in_id,
output_device_id=out_id,
output_monitor_id=monitor_id,
block_frame=block,
audio_sample_rate=sr,
asio_input_channel=-1,
asio_output_channel=-1,
asio_output_monitor_channel=-1,
)
except Exception:
self.stop()
raise
t0 = time.time()
while not cb.vc.ready:
if self.callbacks is not cb:
raise RuntimeError("시작하는 중에 정지했습니다.")
proc = getattr(cb.vc, "_process", None)
if proc is not None and not proc.is_alive():
self.stop()
raise RuntimeError("모델을 불러오다 변환 작업이 멈췄습니다. 모델 파일을 확인해 주세요.")
if time.time() - t0 > 300:
self.stop()
raise RuntimeError("모델을 5분 안에 불러오지 못했습니다.")
on_status(f"모델 불러오는 중... {int(time.time() - t0)}초")
time.sleep(0.5)
def set_pitch(self, pitch: int):
if self.callbacks is not None:
self.callbacks.audio.f0_up_key = pitch
def latency_ms(self) -> float:
return float(getattr(self.callbacks.audio, "latency", 0) or 0) if self.callbacks else 0.0
def stop(self):
cb, self.callbacks = self.callbacks, None
if cb is None:
return
try:
cb.audio.stop()
finally:
cb.vc.stop()
class App:
def __init__(self, root: tk.Tk):
self.root = root
self.conv = Converter()
self.events = queue.Queue() # 작업 스레드 → 화면 (tk 는 메인 스레드에서만 만진다)
self.settings = load_json(SETTINGS, {})
self.models = []
root.title("실시간 음성 변환기")
root.minsize(560, 520)
root.protocol("WM_DELETE_WINDOW", self.close)
pad = dict(padx=10, pady=4)
f = ttk.Frame(root)
f.pack(fill="both", expand=True, padx=8, pady=8)
ttk.Label(f, text="목소리 모델").grid(row=0, column=0, sticky="w", **pad)
self.model_list = tk.Listbox(f, height=8, exportselection=False)
self.model_list.grid(row=1, column=0, columnspan=3, sticky="nsew", padx=10)
self.model_list.bind("<<ListboxSelect>>", lambda e: self.on_model())
ttk.Button(f, text="새로고침", command=self.load_models).grid(row=0, column=2, sticky="e", **pad)
self.model_info = ttk.Label(f, text="", foreground="#555")
self.model_info.grid(row=2, column=0, columnspan=3, sticky="w", **pad)
ttk.Label(f, text="내 목소리 성별").grid(row=3, column=0, sticky="w", **pad)
self.my_gender = tk.StringVar(value=self.settings.get("my_gender", "male"))
g = ttk.Frame(f)
g.grid(row=3, column=1, columnspan=2, sticky="w")
for k, v in GENDERS.items():
ttk.Radiobutton(g, text=v, value=k, variable=self.my_gender, command=self.on_model).pack(side="left", padx=4)
ttk.Label(f, text="음높이 (반음)").grid(row=4, column=0, sticky="w", **pad)
self.pitch = tk.IntVar(value=0)
self.pitch_scale = tk.Scale(f, from_=-24, to=24, orient="horizontal", variable=self.pitch, command=lambda v: self.conv.set_pitch(int(float(v))))
self.pitch_scale.grid(row=4, column=1, columnspan=2, sticky="ew", padx=10)
ttk.Label(f, text="성별이 다른 모델을 고르면 ±12 로 자동으로 맞춥니다. 켜 둔 채로 바꿔도 됩니다.", foreground="#555").grid(row=5, column=0, columnspan=3, sticky="w", padx=10)
self.in_dev, self.out_dev, self.mon_dev = tk.StringVar(), tk.StringVar(), tk.StringVar()
self.use_monitor = tk.BooleanVar(value=self.settings.get("use_monitor", False))
ttk.Label(f, text="마이크 (입력)").grid(row=6, column=0, sticky="w", **pad)
self.in_box = ttk.Combobox(f, textvariable=self.in_dev, state="readonly")
self.in_box.grid(row=6, column=1, columnspan=2, sticky="ew", padx=10)
ttk.Label(f, text="출력 (디스코드용은 CABLE Input)").grid(row=7, column=0, sticky="w", **pad)
self.out_box = ttk.Combobox(f, textvariable=self.out_dev, state="readonly")
self.out_box.grid(row=7, column=1, columnspan=2, sticky="ew", padx=10)
ttk.Checkbutton(f, text="내 귀로 듣기", variable=self.use_monitor).grid(row=8, column=0, sticky="w", **pad)
self.mon_box = ttk.Combobox(f, textvariable=self.mon_dev, state="readonly")
self.mon_box.grid(row=8, column=1, columnspan=2, sticky="ew", padx=10)
ttk.Label(f, text="지연").grid(row=9, column=0, sticky="w", **pad)
self.latency = tk.StringVar(value=self.settings.get("latency", "보통 (약 0.25초)"))
ttk.Combobox(f, textvariable=self.latency, values=list(LATENCY), state="readonly").grid(row=9, column=1, columnspan=2, sticky="ew", padx=10)
ttk.Label(f, text="잡음 무시 (dB)").grid(row=10, column=0, sticky="w", **pad)
self.threshold = tk.IntVar(value=self.settings.get("threshold", -60))
tk.Scale(f, from_=-90, to=-20, orient="horizontal", variable=self.threshold).grid(row=10, column=1, columnspan=2, sticky="ew", padx=10)
b = ttk.Frame(f)
b.grid(row=11, column=0, columnspan=3, pady=10)
self.start_btn = ttk.Button(b, text="▶ 변환 시작", command=self.start)
self.start_btn.pack(side="left", padx=6)
self.stop_btn = ttk.Button(b, text="■ 정지", command=self.stop, state="disabled")
self.stop_btn.pack(side="left", padx=6)
self.status = ttk.Label(f, text="꺼짐")
self.status.grid(row=12, column=0, columnspan=3, sticky="w", **pad)
f.columnconfigure(1, weight=1)
f.rowconfigure(1, weight=1)
self.load_models()
self.load_devices()
self.tick()
# ---- 목록 ----
def load_models(self):
self.models = list_models()
self.model_list.delete(0, "end")
for m in self.models:
self.model_list.insert("end", m.label)
if not self.models:
self.model_info.config(text="모델이 없습니다. train.bat 로 학습하거나 examples.bat 로 예시 모델을 만들어 주세요.")
return
last = self.settings.get("model")
i = next((n for n, m in enumerate(self.models) if m.id == last), None)
self.model_list.selection_set(i or 0)
self.on_model(keep_pitch=self.settings.get("pitch") if i is not None else None)
def load_devices(self):
try:
self.ins, self.outs = list_devices()
except Exception as e:
self.ins, self.outs = {}, {}
self.status.config(text=f"오디오 장치를 읽지 못했습니다: {e}")
self.in_box["values"] = list(self.ins)
self.out_box["values"] = list(self.outs)
self.mon_box["values"] = list(self.outs)
for var, choices, key in ((self.in_dev, self.ins, "input"), (self.out_dev, self.outs, "output"), (self.mon_dev, self.outs, "monitor")):
saved = self.settings.get(key)
var.set(saved if saved in choices else next(iter(choices), ""))
def selected(self):
sel = self.model_list.curselection()
return self.models[sel[0]] if sel else None
def on_model(self, keep_pitch=None):
m = self.selected()
if not m:
return
p = keep_pitch if isinstance(keep_pitch, int) else auto_pitch(self.my_gender.get(), m.gender)
self.pitch.set(p)
self.conv.set_pitch(p)
extra = " · ".join(x for x in (m.source, m.license, "검색 인덱스 있음" if m.index else "인덱스 없음") if x)
self.model_info.config(text=extra)
if self.conv.running:
self.status.config(text="모델을 바꾸려면 정지 후 다시 시작해 주세요. (음높이는 바로 바뀝니다)")
# ---- 시작/정지 ----
def start(self):
m = self.selected()
if not m:
messagebox.showwarning("음성 변환기", "목소리 모델을 골라 주세요.")
return
if self.in_dev.get() not in self.ins or self.out_dev.get() not in self.outs:
messagebox.showwarning("음성 변환기", "마이크와 출력 장치를 골라 주세요.")
return
mon = self.outs.get(self.mon_dev.get()) if self.use_monitor.get() else None
if self.use_monitor.get() and mon is None:
messagebox.showwarning("음성 변환기", "내 귀로 들을 장치를 골라 주세요.")
return
self.save_settings(m)
self.start_btn.config(state="disabled")
args = (m, self.pitch.get(), self.ins[self.in_dev.get()], self.outs[self.out_dev.get()], mon,
LATENCY.get(self.latency.get(), 250), self.threshold.get(), 0.5)
def run():
try:
self.conv.start(*args, on_status=lambda s: self.events.put(("status", s)))
self.events.put(("started", m))
except Exception as e:
self.events.put(("failed", e))
threading.Thread(target=run, daemon=True).start()
def on_started(self, m):
self.running_name = m.name
self.stop_btn.config(state="normal")
self.status.config(text=f"● 변환 중: {m.name}")
def on_failed(self, e):
self.start_btn.config(state="normal")
self.stop_btn.config(state="disabled")
self.status.config(text="꺼짐")
messagebox.showerror("음성 변환기", f"시작하지 못했습니다.\n{e}")
def stop(self):
self.conv.stop()
self.start_btn.config(state="normal")
self.stop_btn.config(state="disabled")
self.status.config(text="꺼짐")
def tick(self):
while True:
try:
kind, val = self.events.get_nowait()
except queue.Empty:
break
if kind == "status":
self.status.config(text=val)
elif kind == "started":
self.on_started(val)
elif kind == "failed":
self.on_failed(val)
if self.conv.running and str(self.stop_btn["state"]) == "normal":
self.status.config(text=f"● 변환 중: {self.running_name} · 처리 {self.conv.latency_ms():.0f}ms")
self.root.after(200, self.tick)
def save_settings(self, m):
self.settings.update(model=m.id, pitch=self.pitch.get(), my_gender=self.my_gender.get(), input=self.in_dev.get(),
output=self.out_dev.get(), monitor=self.mon_dev.get(), use_monitor=self.use_monitor.get(),
latency=self.latency.get(), threshold=self.threshold.get())
save_json(SETTINGS, self.settings)
def close(self):
self.conv.stop()
self.root.destroy()
def main():
root = tk.Tk()
try:
use_engine()
App(root)
except SystemExit as e:
root.withdraw()
messagebox.showerror("음성 변환기", str(e))
return 1
root.mainloop()
if __name__ == "__main__":
mp.freeze_support()
sys.exit(main())