Voice Translator with python-venv node

[404background]

I created a flow for a voice translator using the python-venv node.
The recording, transcription, translation, text-to-speech, and playback processes are executed in each venv node.

Here is the movie. Click and start playing.

Here is the flow.

[{"id":"59c1ee19072ac0f3","type":"venv-exec","z":"22eb2b8f4786695c","name":"gTTS","venvconfig":"015784e9e3e0310a","mode":"execute","executable":"gtts-cli.exe","arguments":"","x":1830,"y":2180,"wires":[["32053553150ae1e3"]]},{"id":"828c8a58c173b4f2","type":"inject","z":"22eb2b8f4786695c","name":"","props":[],"repeat":"","crontab":"","once":false,"onceDelay":0.1,"topic":"","x":1690,"y":1800,"wires":[["66af9ebea1245f3a"]]},{"id":"33f94cd2100b6204","type":"debug","z":"22eb2b8f4786695c","name":"debug 329","active":true,"tosidebar":true,"console":false,"tostatus":false,"complete":"false","statusVal":"","statusType":"auto","x":2170,"y":1800,"wires":[]},{"id":"48120ad67b68b1a4","type":"venv","z":"22eb2b8f4786695c","venvconfig":"015784e9e3e0310a","name":"googletrans","code":"from googletrans import Translator\n\ntranslator = Translator()\ntranslated_text = translator.translate(msg['payload'], src='ja', dest='en')\nprint(f\"\\\"{translated_text.text}\\\" --output voice_en.mp3 --lang en\")\n","continuous":false,"x":1850,"y":2100,"wires":[["83a70b33cd9f01e2"]]},{"id":"66af9ebea1245f3a","type":"pip","z":"22eb2b8f4786695c","venvconfig":"015784e9e3e0310a","name":"googletrans","arg":"googletrans","action":"install","tail":false,"x":1850,"y":1800,"wires":[["d2b00f200bc1772d","f12ccf38690c6b8e"]]},{"id":"83a70b33cd9f01e2","type":"change","z":"22eb2b8f4786695c","name":"","rules":[{"t":"change","p":"payload","pt":"msg","from":"/^\"|\"$/g","fromt":"re","to":"","tot":"str"}],"action":"","property":"","from":"","to":"","reg":false,"x":2060,"y":2100,"wires":[["59c1ee19072ac0f3","890fce3e8aae144b"]]},{"id":"32053553150ae1e3","type":"venv","z":"22eb2b8f4786695c","venvconfig":"015784e9e3e0310a","name":"Constant Speed","code":"import pygame\nimport sys\nimport os\n\npygame.mixer.init()\npygame.mixer.music.load('voice_en.mp3')\npygame.mixer.music.play()\n\nwhile pygame.mixer.music.get_busy():\n    pygame.time.Clock().tick(10)\n","continuous":true,"x":2000,"y":2180,"wires":[["9c33edd8393e7ce0"]]},{"id":"9c33edd8393e7ce0","type":"debug","z":"22eb2b8f4786695c","name":"debug 332","active":false,"tosidebar":true,"console":false,"tostatus":false,"complete":"false","statusVal":"","statusType":"auto","x":2190,"y":2180,"wires":[]},{"id":"890fce3e8aae144b","type":"debug","z":"22eb2b8f4786695c","name":"debug 333","active":true,"tosidebar":true,"console":false,"tostatus":false,"complete":"false","statusVal":"","statusType":"auto","x":2270,"y":2100,"wires":[]},{"id":"f944d50419fd5e14","type":"venv","z":"22eb2b8f4786695c","venvconfig":"015784e9e3e0310a","name":"Record","code":"import pyaudio\nimport numpy as np\nimport wave\nimport time\n\n# 設定\nCHUNK = 1024  # チャンクサイズ\nFORMAT = pyaudio.paInt16  # フォーマット\nCHANNELS = 1  # モノラル録音\nRATE = 16000  # サンプリングレート\nSILENCE_THRESHOLD = 2000  # 音量の閾値（発声の終わりを判定する音量）\nSILENCE_DURATION = 2  # 無音が続く時間（秒）\nOUTPUT_FILENAME = \"output.wav\"  # 保存するファイル名\n\n# PyAudioオブジェクトの作成\np = pyaudio.PyAudio()\n\n# 入力ストリームの開始\nstream = p.open(format=FORMAT,\n                channels=CHANNELS,\n                rate=RATE,\n                input=True,\n                frames_per_buffer=CHUNK)\n\nframes = []  # 録音したフレームを格納\nsilence_start = None  # 無音開始時刻\nsound_detected = False  # 一度音声が検出されたかどうか\nrecording = True  # 録音状態\n\nwhile recording:\n    data = stream.read(CHUNK)  # 音声データの読み込み\n    frames.append(data)\n\n    # 音量（ピーク）を計算\n    audio_data = np.frombuffer(data, dtype=np.int16)\n    peak = np.max(np.abs(audio_data))  # ピーク音量\n\n    # 音量が閾値を超えた場合\n    if peak > SILENCE_THRESHOLD:\n        sound_detected = True  # 音声が検出された\n        silence_start = None  # 無音の開始をリセット\n    elif sound_detected:  # 一度音声が検出された後\n        if silence_start is None:\n            silence_start = time.time()  # 無音の開始時間を記録\n        elif time.time() - silence_start > SILENCE_DURATION:\n            # 無音が閾値時間続いたら録音終了\n            recording = False\n\n# ストリームを停止し、終了\nstream.stop_stream()\nstream.close()\np.terminate()\n\n# 録音したデータをファイルに保存\nwith wave.open(OUTPUT_FILENAME, 'wb') as wf:\n    wf.setnchannels(CHANNELS)\n    wf.setsampwidth(p.get_sample_size(FORMAT))\n    wf.setframerate(RATE)\n    wf.writeframes(b''.join(frames))\n    print(OUTPUT_FILENAME)\n","continuous":true,"x":1840,"y":1940,"wires":[["3487be5890273d99","e532cb3136452bb6"]]},{"id":"435bdfe73c985be1","type":"inject","z":"22eb2b8f4786695c","name":"Start","props":[],"repeat":"","crontab":"","once":false,"onceDelay":0.1,"topic":"","x":1690,"y":1940,"wires":[["f944d50419fd5e14"]]},{"id":"3487be5890273d99","type":"debug","z":"22eb2b8f4786695c","name":"debug 334","active":false,"tosidebar":true,"console":false,"tostatus":false,"complete":"false","statusVal":"","statusType":"auto","x":1990,"y":1940,"wires":[]},{"id":"e532cb3136452bb6","type":"venv","z":"22eb2b8f4786695c","venvconfig":"015784e9e3e0310a","name":"faster-whisper","code":"from faster_whisper import WhisperModel\n\n# モデルのロード\nmodel_path = \"base\"  # 使用するモデル（例: small, medium, large）\nmodel = WhisperModel(model_path, device=\"cpu\", compute_type=\"int8\")  # CPUで実行（GPUを使う場合は \"cuda\"）\n# model = WhisperModel(model_path, device=\"cuda\")\n\n# 音声ファイルのパス\naudio_file = \"output.wav\"\n\n# 文字起こしの実行\nsegments, info = model.transcribe(audio_file, beam_size=5, language=\"ja\")\n\n# 各セグメントを表示\nfor segment in segments:\n    print(f\"{segment.text}\")\n","continuous":false,"x":1860,"y":2020,"wires":[["cf3df149ecd791b1","48120ad67b68b1a4"]]},{"id":"cf3df149ecd791b1","type":"debug","z":"22eb2b8f4786695c","name":"debug 335","active":true,"tosidebar":true,"console":false,"tostatus":false,"complete":"false","statusVal":"","statusType":"auto","x":2050,"y":2020,"wires":[]},{"id":"2e07579924bf1ce6","type":"inject","z":"22eb2b8f4786695c","name":"","props":[],"repeat":"","crontab":"","once":false,"onceDelay":0.1,"topic":"","x":1690,"y":2020,"wires":[["e532cb3136452bb6"]]},{"id":"6f5bb647dc9fd6a6","type":"comment","z":"22eb2b8f4786695c","name":"Translate Voice","info":"","x":1700,"y":1880,"wires":[]},{"id":"01be8211b9a8efb5","type":"pip","z":"22eb2b8f4786695c","venvconfig":"015784e9e3e0310a","name":"pyaudio faster-whisper","arg":"pyaudio faster-whisper","action":"install","tail":false,"x":1880,"y":1760,"wires":[["16a28c4417c8fe1a"]]},{"id":"16a28c4417c8fe1a","type":"debug","z":"22eb2b8f4786695c","name":"debug 336","active":true,"tosidebar":true,"console":false,"tostatus":false,"complete":"false","statusVal":"","statusType":"auto","x":2090,"y":1760,"wires":[]},{"id":"b970930ae8e15301","type":"inject","z":"22eb2b8f4786695c","name":"","props":[],"repeat":"","crontab":"","once":false,"onceDelay":0.1,"topic":"","x":1690,"y":1760,"wires":[["01be8211b9a8efb5"]]},{"id":"0a150480aa0990f3","type":"comment","z":"22eb2b8f4786695c","name":"Install Packages","info":"","x":1700,"y":1700,"wires":[]},{"id":"d2b00f200bc1772d","type":"pip","z":"22eb2b8f4786695c","venvconfig":"015784e9e3e0310a","name":"Audio","arg":"pyaudio numpy pydub gTTS pygame","action":"install","tail":false,"x":2010,"y":1800,"wires":[["33f94cd2100b6204"]]},{"id":"f12ccf38690c6b8e","type":"debug","z":"22eb2b8f4786695c","name":"debug 337","active":true,"tosidebar":true,"console":false,"tostatus":false,"complete":"false","statusVal":"","statusType":"auto","x":2030,"y":1840,"wires":[]},{"id":"015784e9e3e0310a","type":"venv-config","venvname":"AI","version":"3.10"}]