voice-pro
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.
File Explorer
Download Latest Version (.zip)- bug_report.md
- feature_request.md
- FUNDING.yml
- __init__.py
- abus_aicover.py
- abus_app_aria.py
- abus_app_gulliver.py
- abus_app_kara.py
- abus_app_upscaler.py
- abus_app_voice.py
- abus_asr_faster_whisper.py
- abus_asr_parameters.py
- abus_asr_whisper.py
- abus_asr_whisper_timestamped.py
- abus_audio.py
- abus_batch.py
- abus_config.py
- abus_demucs.py
- abus_downloader.py
- abus_ffmpeg.py
- abus_files.py
- abus_genuine.py
- abus_hf.py
- abus_hf_file.py
- abus_hf_files-gulliver.json
- abus_hf_files-kara.json
- abus_hf_files-voice.json
- abus_live.py
- abus_mdx.py
- abus_nlp_spacy.py
- abus_nlp_stanza.py
- abus_path.py
- abus_rvc.py
- abus_subtitle.py
- abus_text.py
- abus_translate_azure.py
- abus_translate_deep.py
- abus_tts_azure.py
- abus_tts_cosyvoice.py
- abus_tts_edge.py
- abus_tts_f5.py
- abus_tts_f5_models.json
- abus_tts_kokoro.py
- abus_tts_rvc.py
- abus_voice_celeb.py
- abus_voice_kokoro.py
- abus_voice_ms.py
- abus_vsr.py
- config-user.json5
- gradio_aicover.py
- gradio_asr.py
- gradio_batch_tts.py
- gradio_demixing.py
- gradio_gulliver.py
- gradio_kara.py
- gradio_live_translate.py
- gradio_rvc.py
- gradio_translate.py
- gradio_tts_cosyvoice.py
- gradio_tts_edge.py
- gradio_tts_f5.py
- gradio_tts_kokoro.py
- gradio_tts_rvc.py
- gradio_voice_celeb.py
- gradio_voice_kokoro.py
- gradio_voice_ms.py
- gradio_vsr.py
- tab_aicover.py
- tab_batch_tts.py
- tab_demixing.py
- tab_gulliver.py
- tab_karaoke.py
- tab_live_translate.py
- tab_rvc.py
- tab_subtitle.py
- tab_translate.py
- tab_tts_cosyvoice.py
- tab_tts_edge.py
- tab_tts_f5_multi.py
- tab_tts_f5_single.py
- tab_tts_kokoro.py
- tab_tts_rvc.py
- tab_vsr.py
- average_model.py
- export_jit.py
- export_onnx.py
- train.py
- __init__.py
- cosyvoice.py
- frontend.py
- model.py
- __init__.py
- dataset.py
- processor.py
- dit.py
- modules.py
- decoder.py
- flow.py
- flow_matching.py
- length_regulator.py
- discriminator.py
- f0_predictor.py
- generator.py
- hifigan.py
- llm.py
- multilingual_zh_ja_yue_char_del.tiktoken
- tokenizer.py
- __init__.py
- activation.py
- attention.py
- convolution.py
- decoder.py
- decoder_layer.py
- embedding.py
- encoder.py
- encoder_layer.py
- label_smoothing_loss.py
- positionwise_feed_forward.py
- subsampling.py
- upsample_encoder.py
- __init__.py
- class_utils.py
- common.py
- executor.py
- file_utils.py
- frontend_utils.py
- losses.py
- mask.py
- onnx.py
- scheduler.py
- train_utils.py
- cosyvoice2.py
- __init__.py
- 2026-07-13.v4.0.0-release.naver.kor.md
- README.md
- Dilraba Dilmurat.jpg
- Jolin Tsai.jpg
- Kris Wu.jpg
- Li Yifeng.jpg
- Yang Mi.jpg
- Zhao Liying.jpg
- Andrew Bustamante.jpg
- Andrew Huberman.jpg
- Avi Loeb.jpg
- Ben Shapiro.jpg
- Brett Johnson.jpg
- Brian Keating.jpg
- Coffeezilla.jpg
- Dan Carlin.jpg
- David Buss.jpg
- David Fravor.jpg
- David Kipping.jpg
- Dennis Whyte.jpg
- Donald Hoffman.jpg
- Donald Trump.jpg
- Douglas Murray.jpg
- Duncan Trussell.jpg
- Elon Musk.jpg
- Garry Nolan.jpg
- Jack Barsky.jpg
- James Sexton.jpg
- Jeff Bezos.jpg
- Joe Rogan.jpg
- John Mearsheimer.jpg
- Jordan Peterson.jpg
- Kanye 'Ye' West.jpg
- Mark Zuckerberg.jpg
- Michael Levin.jpg
- Michael Saylor.jpg
- Michio Kaku.jpg
- MrBeast.jpg
- Nick Lane.jpg
- Paul Rosolie.jpg
- Ryan Graves.jpg
- Sam Altman.jpg
- Sam Harris.jpg
- Stephen Wolfram.jpg
- Tucker Carlson.jpg
- Vitalik Buterin.jpg
- Yuval Harari.jpg
- Ayase Haruka.jpg
- BTS Jin.jpg
- BTS RM.jpg
- IU.jpg
- LeeByungHun.jpg
- LeeJungJae.jpg
- YouJaeSuk.jpg
- ABUS-logo.jpg
- ai_cover.jpg
- Hotpot 0.png
- Hotpot 1.png
- Hotpot 2.png
- Hotpot 3.png
- Hotpot 4.png
- live_translation_bbc.jpg
- main_page.deu.jpg
- main_page.eng.jpg
- main_page.jpn.jpg
- main_page.kor.jpg
- main_page.por.jpg
- main_page.spa.jpg
- main_page.tw.jpg
- main_page.zh.jpg
- main_page_crop.deu.jpg
- main_page_crop.eng.jpg
- main_page_crop.jpn.jpg
- main_page_crop.kor.jpg
- main_page_crop.por.jpg
- main_page_crop.spa.jpg
- main_page_crop.tw.jpg
- main_page_crop.zh.jpg
- microsoft_azure.png
- tts_f5_multi.jpg
- windows_smartscreen_warning.jpg
- celeb-1.jpg
- celeb-2.jpg
- celeb-3.jpg
- Donald Trump.jpg
- MrBeast.jpg
- Sam Altman.jpg
- demo-1.png
- demo-2.png
- demo-3.png
- style.css
- ads.txt
- index.html
- privacy.html
- README.deu.md
- README.eng.md
- README.jpn.md
- README.kor.md
- README.por.md
- README.spa.md
- README.tw.md
- README.zh.md
- terms.html
- htdemucs.yaml
- htdemucs_6s.yaml
- htdemucs_ft.yaml
- mdx_extra.yaml
- model_data.json
- Put voice models here.txt
- silero_vad.onnx
- infer.py
- pipeline.py
- 32k.json
- 32k_v2.json
- 40k.json
- 48k.json
- 48k_v2.json
- __init__.py
- attentions.py
- commons.py
- models.py
- models_onnx.py
- models_onnx_moess.py
- modules.py
- transforms.py
- __init__.py
- mdx.py
- my_utils.py
- rmvpe.py
- rvc.py
- trainset_preprocess_pipeline_print.py
- vc_infer_pipeline.py
- NotoSans-Black.woff
- NotoSans-Black.woff2
- NotoSans-BlackItalic.woff
- NotoSans-BlackItalic.woff2
- NotoSans-Bold.woff
- NotoSans-Bold.woff2
- NotoSans-BoldItalic.woff
- NotoSans-BoldItalic.woff2
- NotoSans-ExtraBold.woff
- NotoSans-ExtraBold.woff2
- NotoSans-ExtraBoldItalic.woff
- NotoSans-ExtraBoldItalic.woff2
- NotoSans-ExtraLight.woff
- NotoSans-ExtraLight.woff2
- NotoSans-ExtraLightItalic.woff
- NotoSans-ExtraLightItalic.woff2
- NotoSans-Italic.woff
- NotoSans-Italic.woff2
- NotoSans-Light.woff
- NotoSans-Light.woff2
- NotoSans-LightItalic.woff
- NotoSans-LightItalic.woff2
- NotoSans-Medium.woff
- NotoSans-Medium.woff2
- NotoSans-MediumItalic.woff
- NotoSans-MediumItalic.woff2
- NotoSans-Regular.woff
- NotoSans-Regular.woff2
- NotoSans-SemiBold.woff
- NotoSans-SemiBold.woff2
- NotoSans-SemiBoldItalic.woff
- NotoSans-SemiBoldItalic.woff2
- NotoSans-Thin.woff
- NotoSans-Thin.woff2
- NotoSans-ThinItalic.woff
- NotoSans-ThinItalic.woff2
- stylesheet.css
- chat_style-cai-chat-square.css
- chat_style-cai-chat.css
- chat_style-messenger.css
- chat_style-TheEncrypted777.css
- chat_style-wpp.css
- html_4chan_style.css
- html_instruct_style.css
- html_readable_style.css
- main.css
- __init__.py
- _explorers.py
- mdx.py
- mdx_extra.py
- mdx_refine.py
- mmi.py
- mmi_ft.py
- repro.py
- repro_ft.py
- sdx23.py
- files.txt
- hdemucs_mmi.yaml
- htdemucs.yaml
- htdemucs_6s.yaml
- htdemucs_ft.yaml
- mdx.yaml
- mdx_extra.yaml
- mdx_extra_q.yaml
- mdx_q.yaml
- repro_mdx_a.yaml
- repro_mdx_a_hybrid_only.yaml
- repro_mdx_a_time_only.yaml
- __init__.py
- __main__.py
- api.py
- apply.py
- audio.py
- augment.py
- demucs.py
- distrib.py
- ema.py
- evaluate.py
- hdemucs.py
- htdemucs.py
- pretrained.py
- py.typed
- repitch.py
- repo.py
- separate.py
- solver.py
- spec.py
- states.py
- svd.py
- train.py
- transformer.py
- utils.py
- wav.py
- wdemucs.py
- de_DE.json
- en_US.json
- es_ES.json
- ja_JP.json
- ko_KR.json
- pt_BR.json
- zh_CN.json
- zh_TW.json
- i18n.py
- locale_diff.py
- scan_i18n.py
- main.js
- save_files.js
- show_controls.js
- switch_tabs.js
- update_big_picture.js
- __init__.py
- config.py
- iso_country_codes.py
- progressListener.py
- shared.py
- ui.py
- vad.py
- whisperProgressHook.py
- default.yaml
- model_checkpoint.yaml
- model_summary.yaml
- none.yaml
- rich_progress_bar.yaml
- hi-fi_en-US_female.yaml
- ljspeech.yaml
- vctk.yaml
- default.yaml
- fdr.yaml
- limit.yaml
- overfit.yaml
- profiler.yaml
- hifi_dataset_piper_phonemizer.yaml
- ljspeech.yaml
- ljspeech_min_memory.yaml
- multispeaker.yaml
- default.yaml
- mnist_optuna.yaml
- default.yaml
- .gitkeep
- aim.yaml
- comet.yaml
- csv.yaml
- many_loggers.yaml
- mlflow.yaml
- neptune.yaml
- tensorboard.yaml
- wandb.yaml
- default.yaml
- default.yaml
- default.yaml
- adam.yaml
- matcha.yaml
- default.yaml
- cpu.yaml
- ddp.yaml
- ddp_sim.yaml
- default.yaml
- gpu.yaml
- mps.yaml
- __init__.py
- eval.yaml
- train.yaml
- __init__.py
- __init__.py
- text_mel_datamodule.py
- __init__.py
- config.py
- denoiser.py
- env.py
- LICENSE
- meldataset.py
- models.py
- README.md
- xutils.py
- __init__.py
- decoder.py
- flow_matching.py
- text_encoder.py
- transformer.py
- __init__.py
- baselightningmodule.py
- matcha_tts.py
- __init__.py
- export.py
- infer.py
- __init__.py
- cleaners.py
- numbers.py
- symbols.py
- __init__.py
- core.pyx
- setup.py
- __init__.py
- audio.py
- generate_data_statistics.py
- instantiators.py
- logging_utils.py
- model.py
- pylogger.py
- rich_utils.py
- utils.py
- __init__.py
- app.py
- cli.py
- train.py
- VERSION
- .gitkeep
- schedule.sh
- .env.example
- .gitignore
- .pre-commit-config.yaml
- .project-root
- .pylintrc
- data
- LICENSE
- Makefile
- MANIFEST.in
- pyproject.toml
- README.md
- requirements.txt
- setup.py
- synthesis.ipynb
- .env.example
- .gitattributes
- .gitignore
- .python-version
- CLAUDE.md
- configure.bat
- configure.sh
- LICENSE
- one_click.py
- pyproject.toml
- README.md
- start-abus.py
- start-voice.py
- start.bat
- start.sh
- uninstall.bat
- uninstall.sh
- update.bat
- update.sh
- uv.lock
๐ Installation Guide
1. Get the code
git clone https://github.com/abus-aikorea/voice-pro
Downloads the entire project code from GitHub to your computer.
cd voice-pro
Moves into the project folder you just downloaded.
2. Python
Easy RecommendedPrerequisites
pip install -r third_party/Matcha-TTS/requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
jupyter notebook
Launches Jupyter in your browser so you can open and run the notebook (.ipynb) files.
If it runs without errors and prints output in the terminal, it worked.
3. Make
MediumPrerequisites
- Git Needed to download the project code from GitHub.
- Make Usually pre-installed on Linux/macOS. On Windows, install separately (e.g. via MSYS2 or WSL).
cd third_party/Matcha-TTS
This project's files live in a subfolder, so move into it first.
make
Compiles the code based on the generated build configuration to produce an executable.
If it finishes without errors, it worked. Try running the generated executable directly.
// repository documentation
Was this content helpful?
(0 ratings)