import gradio as gr from TTS.api import TTS tts = TTS("tts_models/multilingual/multi-dataset/xtts_v1") tts.to("cuda") def predict(prompt, language, audio_file_pth, agree): tts.tts_to_file( text=prompt, file_path="output.wav", speaker_wav=audio_file_pth, language=language, ) return gr.make_waveform( audio="output.wav", ), gr.Audio(value="output.wav") title = "Coqui🐸 XTTS" description = """ XTTS is a Voice generation model that lets you clone voices into different languages by using just a quick 3-second audio clip.
Built on Tortoise, XTTS has important model changes that make cross-language voice cloning and multi-lingual speech generation super easy.
This is the same model that powers Coqui Studio, and Coqui API, however we apply a few tricks to make it faster and support streaming inference.

For faster inference without waiting in the queue, you should duplicate this space and upgrade to GPU via the settings.
Duplicate Space

""" article = """

By using this demo you agree to the terms of the Coqui Public Model License at https://coqui.ai/cpml

""" examples = [ [ "Once when I was six years old I saw a magnificent picture.", "en", "examples/female.wav", ], [ "Lorsque j'avais six ans j'ai vu, une fois, une magnifique image.", "fr", "examples/male.wav", ], [ "Un tempo lontano, quando avevo sei anni, vidi un magnifico disegno.", "it", "examples/female.wav", ], ] gr.Interface( fn=predict, inputs=[ gr.Textbox( label="Text Prompt", info="One or two sentences at a time is better", value="It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.", ), gr.Dropdown( label="Language", info="Select an output language for the synthesised speech", choices=[ "en", "es", "fr", "de", "it", "pt", "pl", "tr", "ru", "nl", "cz", "ar", "zh", ], max_choices=1, value="en", ), gr.Audio( label="Reference Audio", info="Click on the ✎ button to upload your own target speaker audio", type="filepath", value="examples/female.wav", ), gr.Checkbox(label="Agree", value=True, info="I agree to the terms of the Coqui Public Model License at https://coqui.ai/cpml") ], outputs=[ gr.Video(label="Synthesised Waveform"), gr.Audio(label="Synthesised Audio"), ], title=title, description=description, article=article, # examples=examples, ).queue().launch(debug=True)