# ruff: noqa: E402 # Above allows ruff to ignore E402: module level import not at top of file import re import tempfile import click import gradio as gr import numpy as np import soundfile as sf import torchaudio from cached_path import cached_path from transformers import AutoModelForCausalLM, AutoTokenizer try: import spaces USING_SPACES = True except ImportError: USING_SPACES = False def gpu_decorator(func): if USING_SPACES: return spaces.GPU(func) else: return func from f5_tts.model import DiT, UNetT from f5_tts.infer.utils_infer import ( load_vocoder, load_model, preprocess_ref_audio_text, infer_process, remove_silence_for_generated_wav, save_spectrogram, ) vocoder = load_vocoder() # load models F5TTS_model_cfg = dict(dim=1024, depth=22, heads=16, ff_mult=2, text_dim=512, conv_layers=4) F5TTS_ema_model = load_model( DiT, F5TTS_model_cfg, str(cached_path("hf://SWivid/F5-TTS/F5TTS_Base/model_1200000.safetensors")) ) E2TTS_model_cfg = dict(dim=1024, depth=24, heads=16, ff_mult=4) E2TTS_ema_model = load_model( UNetT, E2TTS_model_cfg, str(cached_path("hf://SWivid/E2-TTS/E2TTS_Base/model_1200000.safetensors")) ) DEFAULT_TTS_MODEL = "F5-TTS" tts_model_choice = DEFAULT_TTS_MODEL chat_model_state = None chat_tokenizer_state = None @gpu_decorator def generate_response(messages, model, tokenizer): """Generate response using Qwen""" text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( **model_inputs, max_new_tokens=512, temperature=0.7, top_p=0.95, ) generated_ids = [ output_ids[len(input_ids) :] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] return tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] @gpu_decorator def infer( ref_audio_orig, ref_text, gen_text, model, remove_silence, cross_fade_duration=0.15, speed=1, show_info=gr.Info ): ref_audio, ref_text = preprocess_ref_audio_text(ref_audio_orig, ref_text, show_info=show_info) if model == "F5-TTS": ema_model = F5TTS_ema_model elif model == "E2-TTS": ema_model = E2TTS_ema_model final_wave, final_sample_rate, combined_spectrogram = infer_process( ref_audio, ref_text, gen_text, ema_model, vocoder, cross_fade_duration=cross_fade_duration, speed=speed, show_info=show_info, progress=gr.Progress(), ) # Remove silence if remove_silence: with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as f: sf.write(f.name, final_wave, final_sample_rate) remove_silence_for_generated_wav(f.name) final_wave, _ = torchaudio.load(f.name) final_wave = final_wave.squeeze().cpu().numpy() # Save the spectrogram with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp_spectrogram: spectrogram_path = tmp_spectrogram.name save_spectrogram(combined_spectrogram, spectrogram_path) return (final_sample_rate, final_wave), spectrogram_path with gr.Blocks() as app_credits: gr.Markdown(""" # Credits * [mrfakename](https://github.com/fakerybakery) for the original [online demo](https://huggingface.co/spaces/mrfakename/E2-F5-TTS) * [RootingInLoad](https://github.com/RootingInLoad) for initial chunk generation and podcast app exploration * [jpgallegoar](https://github.com/jpgallegoar) for multiple speech-type generation & voice chat """) with gr.Blocks() as app_tts: gr.Markdown("# Batched TTS") ref_audio_input = gr.Audio(label="Reference Audio", type="filepath") gen_text_input = gr.Textbox(label="Text to Generate", lines=10) generate_btn = gr.Button("Synthesize", variant="primary") with gr.Accordion("Advanced Settings", open=False): ref_text_input = gr.Textbox( label="Reference Text", info="Leave blank to automatically transcribe the reference audio. If you enter text it will override automatic transcription.", lines=2, ) remove_silence = gr.Checkbox( label="Remove Silences", info="The model tends to produce silences, especially on longer audio. We can manually remove silences if needed. Note that this is an experimental feature and may produce strange results. This will also increase generation time.", value=False, ) speed_slider = gr.Slider( label="Speed", minimum=0.3, maximum=2.0, value=1.0, step=0.1, info="Adjust the speed of the audio.", ) cross_fade_duration_slider = gr.Slider( label="Cross-Fade Duration (s)", minimum=0.0, maximum=1.0, value=0.15, step=0.01, info="Set the duration of the cross-fade between audio clips.", ) audio_output = gr.Audio(label="Synthesized Audio") spectrogram_output = gr.Image(label="Spectrogram") @gpu_decorator def basic_tts( ref_audio_input, ref_text_input, gen_text_input, remove_silence, cross_fade_duration_slider, speed_slider, ): return infer( ref_audio_input, ref_text_input, gen_text_input, tts_model_choice, remove_silence, cross_fade_duration_slider, speed_slider, ) generate_btn.click( basic_tts, inputs=[ ref_audio_input, ref_text_input, gen_text_input, remove_silence, cross_fade_duration_slider, speed_slider, ], outputs=[audio_output, spectrogram_output], ) def parse_speechtypes_text(gen_text): # Pattern to find {speechtype} pattern = r"\{(.*?)\}" # Split the text by the pattern tokens = re.split(pattern, gen_text) segments = [] current_style = "Regular" for i in range(len(tokens)): if i % 2 == 0: # This is text text = tokens[i].strip() if text: segments.append({"style": current_style, "text": text}) else: # This is style style = tokens[i].strip() current_style = style return segments with gr.Blocks() as app_multistyle: # New section for multistyle generation gr.Markdown( """ # Multiple Speech-Type Generation This section allows you to generate multiple speech types or multiple people's voices. Enter your text in the format shown below, and the system will generate speech using the appropriate type. If unspecified, the model will use the regular speech type. The current speech type will be used until the next speech type is specified. """ ) with gr.Row(): gr.Markdown( """ **Example Input:** {Regular} Hello, I'd like to order a sandwich please. {Surprised} What do you mean you're out of bread? {Sad} I really wanted a sandwich though... {Angry} You know what, darn you and your little shop! {Whisper} I'll just go back home and cry now. {Shouting} Why me?! """ ) gr.Markdown( """ **Example Input 2:** {Speaker1_Happy} Hello, I'd like to order a sandwich please. {Speaker2_Regular} Sorry, we're out of bread. {Speaker1_Sad} I really wanted a sandwich though... {Speaker2_Whisper} I'll give you the last one I was hiding. """ ) gr.Markdown( "Upload different audio clips for each speech type. The first speech type is mandatory. You can add additional speech types by clicking the 'Add Speech Type' button." ) # Regular speech type (mandatory) with gr.Row(): with gr.Column(): regular_name = gr.Textbox(value="Regular", label="Speech Type Name") regular_insert = gr.Button("Insert", variant="secondary") regular_audio = gr.Audio(label="Regular Reference Audio", type="filepath") regular_ref_text = gr.Textbox(label="Reference Text (Regular)", lines=2) # Additional speech types (up to 99 more) max_speech_types = 100 speech_type_rows = [] speech_type_names = [regular_name] speech_type_audios = [] speech_type_ref_texts = [] speech_type_delete_btns = [] speech_type_insert_btns = [] speech_type_insert_btns.append(regular_insert) for i in range(max_speech_types - 1): with gr.Row(visible=False) as row: with gr.Column(): name_input = gr.Textbox(label="Speech Type Name") delete_btn = gr.Button("Delete", variant="secondary") insert_btn = gr.Button("Insert", variant="secondary") audio_input = gr.Audio(label="Reference Audio", type="filepath") ref_text_input = gr.Textbox(label="Reference Text", lines=2) speech_type_rows.append(row) speech_type_names.append(name_input) speech_type_audios.append(audio_input) speech_type_ref_texts.append(ref_text_input) speech_type_delete_btns.append(delete_btn) speech_type_insert_btns.append(insert_btn) # Button to add speech type add_speech_type_btn = gr.Button("Add Speech Type") # Keep track of current number of speech types speech_type_count = gr.State(value=0) # Function to add a speech type def add_speech_type_fn(speech_type_count): if speech_type_count < max_speech_types - 1: speech_type_count += 1 # Prepare updates for the rows row_updates = [] for i in range(max_speech_types - 1): if i < speech_type_count: row_updates.append(gr.update(visible=True)) else: row_updates.append(gr.update()) else: # Optionally, show a warning row_updates = [gr.update() for _ in range(max_speech_types - 1)] return [speech_type_count] + row_updates add_speech_type_btn.click( add_speech_type_fn, inputs=speech_type_count, outputs=[speech_type_count] + speech_type_rows ) # Function to delete a speech type def make_delete_speech_type_fn(index): def delete_speech_type_fn(speech_type_count): # Prepare updates row_updates = [] for i in range(max_speech_types - 1): if i == index: row_updates.append(gr.update(visible=False)) else: row_updates.append(gr.update()) speech_type_count = max(0, speech_type_count - 1) return [speech_type_count] + row_updates return delete_speech_type_fn # Update delete button clicks for i, delete_btn in enumerate(speech_type_delete_btns): delete_fn = make_delete_speech_type_fn(i) delete_btn.click(delete_fn, inputs=speech_type_count, outputs=[speech_type_count] + speech_type_rows) # Text input for the prompt gen_text_input_multistyle = gr.Textbox( label="Text to Generate", lines=10, placeholder="Enter the script with speaker names (or emotion types) at the start of each block, e.g.:\n\n{Regular} Hello, I'd like to order a sandwich please.\n{Surprised} What do you mean you're out of bread?\n{Sad} I really wanted a sandwich though...\n{Angry} You know what, darn you and your little shop!\n{Whisper} I'll just go back home and cry now.\n{Shouting} Why me?!", ) def make_insert_speech_type_fn(index): def insert_speech_type_fn(current_text, speech_type_name): current_text = current_text or "" speech_type_name = speech_type_name or "None" updated_text = current_text + f"{{{speech_type_name}}} " return gr.update(value=updated_text) return insert_speech_type_fn for i, insert_btn in enumerate(speech_type_insert_btns): insert_fn = make_insert_speech_type_fn(i) insert_btn.click( insert_fn, inputs=[gen_text_input_multistyle, speech_type_names[i]], outputs=gen_text_input_multistyle, ) with gr.Accordion("Advanced Settings", open=False): remove_silence_multistyle = gr.Checkbox( label="Remove Silences", value=False, ) # Generate button generate_multistyle_btn = gr.Button("Generate Multi-Style Speech", variant="primary") # Output audio audio_output_multistyle = gr.Audio(label="Synthesized Audio") @gpu_decorator def generate_multistyle_speech( regular_audio, regular_ref_text, gen_text, *args, ): num_additional_speech_types = max_speech_types - 1 speech_type_names_list = args[:num_additional_speech_types] speech_type_audios_list = args[num_additional_speech_types : 2 * num_additional_speech_types] speech_type_ref_texts_list = args[2 * num_additional_speech_types : 3 * num_additional_speech_types] remove_silence = args[3 * num_additional_speech_types + 1] # Collect the speech types and their audios into a dict speech_types = {"Regular": {"audio": regular_audio, "ref_text": regular_ref_text}} for name_input, audio_input, ref_text_input in zip( speech_type_names_list, speech_type_audios_list, speech_type_ref_texts_list ): if name_input and audio_input: speech_types[name_input] = {"audio": audio_input, "ref_text": ref_text_input} # Parse the gen_text into segments segments = parse_speechtypes_text(gen_text) # For each segment, generate speech generated_audio_segments = [] current_style = "Regular" for segment in segments: style = segment["style"] text = segment["text"] if style in speech_types: current_style = style else: # If style not available, default to Regular current_style = "Regular" ref_audio = speech_types[current_style]["audio"] ref_text = speech_types[current_style].get("ref_text", "") # Generate speech for this segment audio, _ = infer( ref_audio, ref_text, text, tts_model_choice, remove_silence, 0, show_info=print ) # show_info=print no pull to top when generating sr, audio_data = audio generated_audio_segments.append(audio_data) # Concatenate all audio segments if generated_audio_segments: final_audio_data = np.concatenate(generated_audio_segments) return (sr, final_audio_data) else: gr.Warning("No audio generated.") return None generate_multistyle_btn.click( generate_multistyle_speech, inputs=[ regular_audio, regular_ref_text, gen_text_input_multistyle, ] + speech_type_names + speech_type_audios + speech_type_ref_texts + [ remove_silence_multistyle, ], outputs=audio_output_multistyle, ) # Validation function to disable Generate button if speech types are missing def validate_speech_types(gen_text, regular_name, *args): num_additional_speech_types = max_speech_types - 1 speech_type_names_list = args[:num_additional_speech_types] # Collect the speech types names speech_types_available = set() if regular_name: speech_types_available.add(regular_name) for name_input in speech_type_names_list: if name_input: speech_types_available.add(name_input) # Parse the gen_text to get the speech types used segments = parse_speechtypes_text(gen_text) speech_types_in_text = set(segment["style"] for segment in segments) # Check if all speech types in text are available missing_speech_types = speech_types_in_text - speech_types_available if missing_speech_types: # Disable the generate button return gr.update(interactive=False) else: # Enable the generate button return gr.update(interactive=True) gen_text_input_multistyle.change( validate_speech_types, inputs=[gen_text_input_multistyle, regular_name] + speech_type_names, outputs=generate_multistyle_btn, ) with gr.Blocks() as app_chat: gr.Markdown( """ # Voice Chat Have a conversation with an AI using your reference voice! 1. Upload a reference audio clip and optionally its transcript. 2. Load the chat model. 3. Record your message through your microphone. 4. The AI will respond using the reference voice. """ ) if not USING_SPACES: load_chat_model_btn = gr.Button("Load Chat Model", variant="primary") chat_interface_container = gr.Column(visible=False) @gpu_decorator def load_chat_model(): global chat_model_state, chat_tokenizer_state if chat_model_state is None: show_info = gr.Info show_info("Loading chat model...") model_name = "Qwen/Qwen2.5-3B-Instruct" chat_model_state = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) chat_tokenizer_state = AutoTokenizer.from_pretrained(model_name) show_info("Chat model loaded.") return gr.update(visible=False), gr.update(visible=True) load_chat_model_btn.click(load_chat_model, outputs=[load_chat_model_btn, chat_interface_container]) else: chat_interface_container = gr.Column() if chat_model_state is None: model_name = "Qwen/Qwen2.5-3B-Instruct" chat_model_state = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto") chat_tokenizer_state = AutoTokenizer.from_pretrained(model_name) with chat_interface_container: with gr.Row(): with gr.Column(): ref_audio_chat = gr.Audio(label="Reference Audio", type="filepath") with gr.Column(): with gr.Accordion("Advanced Settings", open=False): remove_silence_chat = gr.Checkbox( label="Remove Silences", value=True, ) ref_text_chat = gr.Textbox( label="Reference Text", info="Optional: Leave blank to auto-transcribe", lines=2, ) system_prompt_chat = gr.Textbox( label="System Prompt", value="You are not an AI assistant, you are whoever the user says you are. You must stay in character. Keep your responses concise since they will be spoken out loud.", lines=2, ) chatbot_interface = gr.Chatbot(label="Conversation") with gr.Row(): with gr.Column(): audio_input_chat = gr.Microphone( label="Speak your message", type="filepath", ) audio_output_chat = gr.Audio(autoplay=True) with gr.Column(): text_input_chat = gr.Textbox( label="Type your message", lines=1, ) send_btn_chat = gr.Button("Send") clear_btn_chat = gr.Button("Clear Conversation") conversation_state = gr.State( value=[ { "role": "system", "content": "You are not an AI assistant, you are whoever the user says you are. You must stay in character. Keep your responses concise since they will be spoken out loud.", } ] ) # Modify process_audio_input to use model and tokenizer from state @gpu_decorator def process_audio_input(audio_path, text, history, conv_state): """Handle audio or text input from user""" if not audio_path and not text.strip(): return history, conv_state, "" if audio_path: text = preprocess_ref_audio_text(audio_path, text)[1] if not text.strip(): return history, conv_state, "" conv_state.append({"role": "user", "content": text}) history.append((text, None)) response = generate_response(conv_state, chat_model_state, chat_tokenizer_state) conv_state.append({"role": "assistant", "content": response}) history[-1] = (text, response) return history, conv_state, "" @gpu_decorator def generate_audio_response(history, ref_audio, ref_text, remove_silence): """Generate TTS audio for AI response""" if not history or not ref_audio: return None last_user_message, last_ai_response = history[-1] if not last_ai_response: return None audio_result, _ = infer( ref_audio, ref_text, last_ai_response, tts_model_choice, remove_silence, cross_fade_duration=0.15, speed=1.0, show_info=print, # show_info=print no pull to top when generating ) return audio_result def clear_conversation(): """Reset the conversation""" return [], [ { "role": "system", "content": "You are not an AI assistant, you are whoever the user says you are. You must stay in character. Keep your responses concise since they will be spoken out loud.", } ] def update_system_prompt(new_prompt): """Update the system prompt and reset the conversation""" new_conv_state = [{"role": "system", "content": new_prompt}] return [], new_conv_state # Handle audio input audio_input_chat.stop_recording( process_audio_input, inputs=[audio_input_chat, text_input_chat, chatbot_interface, conversation_state], outputs=[chatbot_interface, conversation_state], ).then( generate_audio_response, inputs=[chatbot_interface, ref_audio_chat, ref_text_chat, remove_silence_chat], outputs=[audio_output_chat], ).then( lambda: None, None, audio_input_chat, ) # Handle text input text_input_chat.submit( process_audio_input, inputs=[audio_input_chat, text_input_chat, chatbot_interface, conversation_state], outputs=[chatbot_interface, conversation_state], ).then( generate_audio_response, inputs=[chatbot_interface, ref_audio_chat, ref_text_chat, remove_silence_chat], outputs=[audio_output_chat], ).then( lambda: None, None, text_input_chat, ) # Handle send button send_btn_chat.click( process_audio_input, inputs=[audio_input_chat, text_input_chat, chatbot_interface, conversation_state], outputs=[chatbot_interface, conversation_state], ).then( generate_audio_response, inputs=[chatbot_interface, ref_audio_chat, ref_text_chat, remove_silence_chat], outputs=[audio_output_chat], ).then( lambda: None, None, text_input_chat, ) # Handle clear button clear_btn_chat.click( clear_conversation, outputs=[chatbot_interface, conversation_state], ) # Handle system prompt change and reset conversation system_prompt_chat.change( update_system_prompt, inputs=system_prompt_chat, outputs=[chatbot_interface, conversation_state], ) with gr.Blocks() as app: gr.Markdown( """ # E2/F5 TTS This is a local web UI for F5 TTS with advanced batch processing support. This app supports the following TTS models: * [F5-TTS](https://arxiv.org/abs/2410.06885) (A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching) * [E2 TTS](https://arxiv.org/abs/2406.18009) (Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS) The checkpoints support English and Chinese. If you're having issues, try converting your reference audio to WAV or MP3, clipping it to 15s, and shortening your prompt. **NOTE: Reference text will be automatically transcribed with Whisper if not provided. For best results, keep your reference clips short (<15s). Ensure the audio is fully uploaded before generating.** """ ) def switch_tts_model(new_choice): global tts_model_choice tts_model_choice = new_choice if not USING_SPACES: choose_tts_model = gr.Radio( choices=[DEFAULT_TTS_MODEL, "E2-TTS"], label="Choose TTS Model", value=DEFAULT_TTS_MODEL ) else: choose_tts_model = gr.Radio( choices=[DEFAULT_TTS_MODEL, "E2-TTS"], label="Choose TTS Model", value=DEFAULT_TTS_MODEL ) choose_tts_model.change( switch_tts_model, inputs=choose_tts_model, ) gr.TabbedInterface( [app_tts, app_multistyle, app_chat, app_credits], ["TTS", "Multi-Speech", "Voice-Chat", "Credits"], ) @click.command() @click.option("--port", "-p", default=None, type=int, help="Port to run the app on") @click.option("--host", "-H", default=None, help="Host to run the app on") @click.option( "--share", "-s", default=False, is_flag=True, help="Share the app via Gradio share link", ) @click.option("--api", "-a", default=True, is_flag=True, help="Allow API access") def main(port, host, share, api): global app print("Starting app...") app.queue(api_open=api).launch(server_name=host, server_port=port, share=share, show_api=api) if __name__ == "__main__": if not USING_SPACES: main() else: app.queue().launch()