impavloh / voiceit

Change the voice of audios using pre-trained streamer voice models using AI.

README Language

🎙️ VoiceIt!

This project uses pre-trained models to change the voice in audio files. The service allows you to upload audio files, select a voice model, and generate a new audio file with the modified voice.

📚 Relevant Information 🚀

You can use VoiceIt directly online on my website https://voiceit.pavloh.com or use your resources and host the project locally by following the steps below.

Requirements

• Python >3.7
• Gradio
• FFmpeg
• FFprobe

🛠️ Installation

1. Clone the repository: git clone https://github.com/impavloh/voiceit.git

2. Change to the project directory: cd voiceit

3. Install the necessary dependencies: pip install -r requirements.txt

4. Create a folder called "models" and import pre-trained models to use later. In this case, you can use my models: https://huggingface.co/ImPavloh/Streamers-AI-Voices

5. Run the main script: python voiceit.py

📝 Usage

1. When running the voiceit.py file, a terminal will open with a link to access the VoiceIt! interface. For example: http://localhost:7860

2. Select a voice model from the dropdown list.

3. Upload an audio file.

4. Click on the "Change voice" button to generate a new audio file with the modified voice.

5. Listen or download the result in the audio player.

6. You can delete the data and restart the process using the "Delete" button.

⚠️ Warning

• Audio files should contain only one voice and be free of noise or background music.
• The conversion time will depend on the duration of the audio and web usage (if used locally it will depend on your resources)

📝 License and Terms of Use

By using this project, you agree to the license and terms of use.

voiceit's Issues

Error al hacer la inferencia:

Buenas, he seguido paso a paso el readme, he agregado mi modelo pero cuando le doy a cambiar voz me sale este error: FileNotFoundError: [WinError 2] El sistema no puede encontrar el archivo especificado: 'd:\prueba\voiceit\inference_output\output.wav' -> 'output.wav'
Junto con más errores:
Traceback (most recent call last):
File "C:\Users\Erik\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\routes.py", line 427, in run_predict
output = await app.get_blocks().process_api(
File "C:\Users\Erik\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1323, in process_api
result = await self.call_function(
File "C:\Users\Erik\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1051, in call_function
prediction = await anyio.to_thread.run_sync(
File "C:\Users\Erik\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "C:\Users\Erik\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "C:\Users\Erik\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 807, in run
result = context.run(func, *args)
File "d:\cabron\voiceit\voiceit.py", line 129, in convert
shutil.move(Path(INFERENCE_OUTPUT_DIRNAME, final_filename), Path(final_filename))
File "C:\Users\Erik\AppData\Local\Programs\Python\Python310\lib\shutil.py", line 836, in move
copy_function(src, real_dst)
File "C:\Users\Erik\AppData\Local\Programs\Python\Python310\lib\shutil.py", line 434, in copy2
copyfile(src, dst, follow_symlinks=follow_symlinks)
File "C:\Users\Erik\AppData\Local\Programs\Python\Python310\lib\shutil.py", line 254, in copyfile
with open(src, 'rb') as fsrc:
He verificado que estén instaladas las dependencias y parece que está todo correcto.
Soy bastante noob en todo esto pero creo que puede ser problema del shutil, puede que el error esté en la linea 129?? Estoy usando Python 3.8 .

filename = filename.split("\\")[-1] no funciona para mi caso

Al final descubrí de dónde venía el problema. Tuve que cambiar:
filename = filename.split("\\")[-1]
por:
filename = filename.split("/")[-1]

O sea, claramente no hacía el split porque la ruta está con / no con .
Si el script se va a ejecutar en Windows debería buscarse la forma más compatible de usar un delimitador de rutas. Sino definir algo como:
PATH_DELIM="/" if os.name == 'nt': PATH_DELIM="\\"
porque de lo contrario vamos a estar siempre teniendo problemas con el delimitador.

Misspelling: ‘module’ instead of ‘modulo Readme file

in English version of readme, modelos should be replaced with models or vise versa.