Pythonで作る日本語対応オーディオ録音アプリ「AudioRecorderApp」：マイク選択・リアルタイム波形・音量メーター付き

import tkinter as tk
from tkinter import ttk, filedialog
import threading
import pyaudio
import wave
import numpy as np
import matplotlib
matplotlib.rcParams['font.family'] = 'Yu Gothic'  # ← 日本語フォント指定
import matplotlib.pyplot as plt
from matplotlib.backends.backend_tkagg import FigureCanvasTkAgg
import time

# ==============================
# EnhancedAudioApp (日本語 UI + マイク選択 + 文字化け修正版)
# ==============================
class EnhancedAudioApp:

    def __init__(self, root):
        self.root = root
        self.root.title("Enhanced Audio Recorder（拡張版）")

        # PyAudio 初期化
        self.p = pyaudio.PyAudio()

        # 録音設定
        self.channels = 1
        self.rate = 44100
        self.chunk = 1024

        # 状態管理
        self.recording = False
        self.frames = []
        self.start_time = 0

        # UI作成
        self.create_widgets()

    # ==========================
    # 🔊 マイクデバイス一覧取得
    # ==========================
    def get_input_devices(self):
        device_list = []
        for i in range(self.p.get_device_count()):
            info = self.p.get_device_info_by_index(i)

            # 入力デバイスのみ
            if info["maxInputChannels"] > 0:
                # name を str に変換して文字化け回避
                name = str(info["name"])
                device_list.append((i, name))
        return device_list

    # ==========================
    # 🎨 UI 構築
    # ==========================
    def create_widgets(self):

        # ─────────────────────────
        # マイクデバイス選択
        # ─────────────────────────
        device_frame = ttk.LabelFrame(self.root, text="マイクデバイス選択")
        device_frame.pack(fill="x", padx=10, pady=5)

        ttk.Label(device_frame, text="入力デバイス: ").pack(side="left")

        self.device_list = self.get_input_devices()
        device_names = [name for idx, name in self.device_list]

        self.device_var = tk.StringVar()
        self.device_box = ttk.Combobox(
            device_frame,
            textvariable=self.device_var,
            values=device_names,
            state="readonly",
            width=50
        )
        self.device_box.pack(side="left", padx=5)

        if device_names:
            self.device_box.current(0)

        # ─────────────────────────
        # 録音ボタン類
        # ─────────────────────────
        btn_frame = tk.Frame(self.root)
        btn_frame.pack(pady=10)

        ttk.Button(btn_frame, text="● 録音開始", command=self.start_recording).grid(row=0, column=0, padx=10)
        ttk.Button(btn_frame, text="■ 停止", command=self.stop_recording).grid(row=0, column=1, padx=10)
        ttk.Button(btn_frame, text="💾 保存", command=self.save_audio).grid(row=0, column=2, padx=10)

        # ─────────────────────────
        # 録音時間
        # ─────────────────────────
        self.time_label = ttk.Label(self.root, text="録音時間: 0.0 秒", font=("Yu Gothic", 12))
        self.time_label.pack()

        # ─────────────────────────
        # 音量バー
        # ─────────────────────────
        volume_frame = ttk.LabelFrame(self.root, text="音量レベル")
        volume_frame.pack(fill="x", padx=10, pady=5)

        self.volume_bar = ttk.Progressbar(volume_frame, orient="horizontal", mode="determinate", length=300)
        self.volume_bar.pack(padx=10, pady=5)

        # ─────────────────────────
        # 波形表示（matplotlib）
        # ─────────────────────────
        fig = plt.Figure(figsize=(6, 3), dpi=100)
        self.ax = fig.add_subplot(111)
        self.ax.set_ylim([-1, 1])
        self.ax.set_title("リアルタイム波形（日本語対応）")
        self.line, = self.ax.plot([], [])

        self.canvas = FigureCanvasTkAgg(fig, master=self.root)
        self.canvas.get_tk_widget().pack()

    # ==========================
    # 🎙 録音開始
    # ==========================
    def start_recording(self):
        if self.recording:
            return

        self.recording = True
        self.frames = []
        self.start_time = time.time()

        # 選択されたデバイス index 取得
        selected_name = self.device_var.get()
        device_index = next(idx for idx, nm in self.device_list if nm == selected_name)

        # PyAudio ストリーム開始
        self.stream = self.p.open(format=pyaudio.paInt16,
                                  channels=self.channels,
                                  rate=self.rate,
                                  input=True,
                                  frames_per_buffer=self.chunk,
                                  input_device_index=device_index)

        threading.Thread(target=self.record).start()
        self.update_time()

    # ==========================
    # ⏱ 録音時間更新
    # ==========================
    def update_time(self):
        if self.recording:
            elapsed = time.time() - self.start_time
            self.time_label.config(text=f"録音時間: {elapsed:.1f} 秒")
            self.root.after(100, self.update_time)

    # ==========================
    # 📈 リアルタイム録音処理
    # ==========================
    def record(self):

        while self.recording:
            data = self.stream.read(self.chunk)
            self.frames.append(data)

            audio_np = np.frombuffer(data, dtype=np.int16).astype(np.float32) / 32768.0

            # ノイズゲート（簡易）
            audio_np[audio_np < 0.01] = 0

            # 音量バー更新
            volume = min(int(np.max(np.abs(audio_np)) * 100), 100)
            self.volume_bar["value"] = volume

            # 波形更新
            self.line.set_data(range(len(audio_np)), audio_np)
            self.ax.set_xlim([0, len(audio_np)])
            self.canvas.draw()

    # ==========================
    # ■ 録音停止
    # ==========================
    def stop_recording(self):
        if not self.recording:
            return

        self.recording = False
        self.stream.stop_stream()
        self.stream.close()

    # ==========================
    # 💾 WAV 保存
    # ==========================
    def save_audio(self):
        if not self.frames:
            return

        file_path = filedialog.asksaveasfilename(
            defaultextension=".wav",
            filetypes=[("WAVファイル", "*.wav")]
        )

        if not file_path:
            return

        wf = wave.open(file_path, "wb")
        wf.setnchannels(self.channels)
        wf.setsampwidth(self.p.get_sample_size(pyaudio.paInt16))
        wf.setframerate(self.rate)
        wf.writeframes(b"".join(self.frames))
        wf.close()

        print("保存しました:", file_path)


# ==============================
# アプリ起動
# ==============================
if __name__ == "__main__":
    root = tk.Tk()
    app = EnhancedAudioApp(root)
    root.mainloop()