hookvision-rk/tools/generate_voices.py

"""使用本机 SAPI 语音合成生成 assets/voices/*.wav"""
import os
import sys

OUTPUT_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "assets", "voices")

VOICES = {
    "hooking.wav": "挂包中",
    "ready.wav": "挂包成功",
    "releasing.wav": "放包中",
    "arrive_1.wav": "到达1号工位",
    "arrive_2.wav": "到达2号工位",
    "arrive_3.wav": "到达3号工位",
    "arrive_4.wav": "到达4号工位",
    "arrive_5.wav": "到达5号工位",
}


def main():
    os.makedirs(OUTPUT_DIR, exist_ok=True)

    import win32com.client

    speaker = win32com.client.Dispatch("SAPI.SpVoice")

    SSFMCreateForWrite = 3
    SAFT16kHz16BitMono = 4

    for filename, text in VOICES.items():
        path = os.path.join(OUTPUT_DIR, filename)
        stream = win32com.client.Dispatch("SAPI.SpFileStream")
        af = win32com.client.Dispatch("SAPI.SpAudioFormat")
        af.Type = SAFT16kHz16BitMono
        stream.Format = af
        stream.Open(path, SSFMCreateForWrite)
        speaker.AudioOutputStream = stream
        speaker.Speak(text)
        stream.Close()
        print(f"生成: {path}")


if __name__ == "__main__":
    main()