🔒 Was recommended Kokoro TTS, lack of much documentation has me a little flustered.

[hearty pike]

Hey @ionic sinew!

Please edit your message to use a code block

Add a py after the three backticks.

```py
print('Hello, world!')
```

This will result in the following:

print('Hello, world!')```

@ionic sinew

Python help channel opened

Remember to:

• Ask your Python question, not if you can ask or if there's an expert who can help.
• Show a code sample as text (rather than a screenshot) and the error message, if you've got one.
• Explain what you expect to happen and what actually happens.

:warning: Do not pip install anything that isn't related to your question, especially if asked to over DMs.

Closes after a period of inactivity, or when you send !close.

[ionic sinew]

from kokoro import KPipeline, KModel
import torch
from scipy.io import wavfile

def save_audio(audio: torch.Tensor, filename: str):
    """Helper function to save audio tensor as WAV file"""
    # Ensure audio is on CPU and in the right format
    audio_cpu = audio.cpu().numpy()
    
    # Save using scipy.io.wavfile
    wavfile.write(
        filename,
        24000,  # Kokoro uses 24kHz sample rate
        audio_cpu
    )
    print(f"Audio saved as '{filename}'")

def main():
    # Initialize pipeline with American English
    pipeline = KPipeline(lang_code='a')
        
    # Example 2: Using generate_from_tokens with pre-processed tokens
    #  get the tokens through G2P or any other method
    text = "How are you today? I am doing reasonably well, thank you for asking"
    _, tokens = pipeline.g2p(text)
    
    # Then generate from tokens
    for result in pipeline.generate_from_tokens(
        tokens=tokens,
        voice="af_bella",
        speed=1.0
    ):
        save_audio(result.audio, f'token_output_{hash(result.phonemes)}.wav')

if __name__ == "__main__":
    main()

I'm a bit of a complete newbie so things are a little iffy to me to begin with but would I be mistaken if a simple return statement would work on the save_audio variable to use it to convert through RVC/use it for real time TTS in general?

[hearty pike]

@ionic sinew

Python help channel closed for inactivity

This help channel has been closed. Feel free to create a new post in #1035199133436354600. To maximize your chances of getting a response, check out this guide on asking good questions.