I’m creating a chatbot that talks with voice using llama3.1, whisper, openvoice v2.

However, after getting the text from Lamar 3.1 to answer my question, I see an error converting it from OpenVoice v2 to voice.

OSError: [WinError 6] Handle is invalid

”’
def text_to_speech(text, reference_speaker, language=’ja’):
tone_color_converter, device, output_dir = init_openvoice()

# Extract target speaker embedding from the reference speaker
target_se, audio_name = se_extractor.get_se(reference_speaker, tone_color_converter, vad=True)

# Use MeloTTS for base speaker text-to-speech generation
model = TTS(language=language, device=device)
speaker_ids = model.hps.data.spk2id

base_speaker_key = list(speaker_ids.keys())[0]  # Use the first base speaker for simplicity
speaker_id = speaker_ids[base_speaker_key]

# Generate the base TTS audio
src_path = f'{output_dir}/tmp.wav'
model.tts_to_file(text, speaker_id, src_path, speed=1.0)

# Run tone color conversion to match the reference speaker's voice
save_path = f'{output_dir}/final_output.wav'
source_se = torch.load(f'checkpoints_v2/base_speakers/ses/{base_speaker_key}.pth', map_location=device)

tone_color_converter.convert(
    audio_src_path=src_path, 
    src_se=source_se, 
    tgt_se=target_se, 
    output_path=save_path,
    message="@MyShell"
)

”’

The error occurs in that area.

model.tts_to_file(text, speaker_id, src_path, speed=1.0)

The work environment is Windows 11, Virtual Environments vsCode…..

At first, I confirmed that gpu is not working in the virtual environment. I made gpu available again in the virtual environment because I was wondering if that was a problem. However, the same error occurred. The paths in the file were not wrong.