Function build_ui

webui.py:94–221

(model_dir, device=0)

def build_ui(model_dir, device=0):

    # Initialize model
    model = initialize_model(model_dir, device=device)

    # Define callback function for voice cloning
    def voice_clone(text, prompt_text, prompt_wav_upload, prompt_wav_record):
        """
        Gradio callback to clone voice using text and optional prompt speech.
        - text: The input text to be synthesised.
        - prompt_text: Additional textual info for the prompt (optional).
        - prompt_wav_upload/prompt_wav_record: Audio files used as reference.
        """
        prompt_speech = prompt_wav_upload if prompt_wav_upload else prompt_wav_record
        prompt_text_clean = None if len(prompt_text) < 2 else prompt_text

        audio_output_path = run_tts(
            text,
            model,
            prompt_text=prompt_text_clean,
            prompt_speech=prompt_speech
        )
        return audio_output_path

    # Define callback function for creating new voices
    def voice_creation(text, gender, pitch, speed):
        """
        Gradio callback to create a synthetic voice with adjustable parameters.
        - text: The input text for synthesis.
        - gender: 'male' or 'female'.
        - pitch/speed: Ranges mapped by LEVELS_MAP_UI.
        """
        pitch_val = LEVELS_MAP_UI[int(pitch)]
        speed_val = LEVELS_MAP_UI[int(speed)]
        audio_output_path = run_tts(
            text,
            model,
            gender=gender,
            pitch=pitch_val,
            speed=speed_val
        )
        return audio_output_path

    with gr.Blocks() as demo:
        # Use HTML for centered title
        gr.HTML('<h1 style="text-align: center;">Spark-TTS by SparkAudio</h1>')
        with gr.Tabs():
            # Voice Clone Tab
            with gr.TabItem("Voice Clone"):
                gr.Markdown(
                    "### Upload reference audio or recording （上传参考音频或者录音）"
                )

                with gr.Row():
                    prompt_wav_upload = gr.Audio(
                        sources="upload",
                        type="filepath",
                        label="Choose the prompt audio file, ensuring the sampling rate is no lower than 16kHz.",