Ultimate-TTS-Studio-SUP3R-Edition
π’ NVIDIA ONLY β All-in-One TTS App with Kokoro, KittenTTS, Higgs audio, Chatterbox, Fish-Speech, F5 & index-tts & indextts2, Supports Conversation Mode & eBook-to-Audiobook. All features work across all engines in a unified interface except vibe voice which is it's own app panel.
νμΌ νμκΈ°
μ΅μ’ λ²μ λ€μ΄λ‘λ (.zip)- __init__.cpython-310.pyc
- tts.cpython-310.pyc
- vc.cpython-310.pyc
- __init__.cpython-310.pyc
- const.cpython-310.pyc
- decoder.cpython-310.pyc
- f0_predictor.cpython-310.pyc
- flow.cpython-310.pyc
- flow_matching.cpython-310.pyc
- hifigan.cpython-310.pyc
- s3gen.cpython-310.pyc
- xvector.cpython-310.pyc
- decoder.cpython-310.pyc
- flow_matching.cpython-310.pyc
- transformer.cpython-310.pyc
- decoder.py
- flow_matching.py
- text_encoder.py
- transformer.py
- __init__.cpython-310.pyc
- activation.cpython-310.pyc
- attention.cpython-310.pyc
- convolution.cpython-310.pyc
- embedding.cpython-310.pyc
- encoder_layer.cpython-310.pyc
- positionwise_feed_forward.cpython-310.pyc
- subsampling.cpython-310.pyc
- upsample_encoder.cpython-310.pyc
- __init__.py
- activation.py
- attention.py
- convolution.py
- embedding.py
- encoder_layer.py
- positionwise_feed_forward.py
- subsampling.py
- upsample_encoder.py
- class_utils.cpython-310.pyc
- mask.cpython-310.pyc
- mel.cpython-310.pyc
- class_utils.py
- intmeanflow.py
- mask.py
- mel.py
- __init__.py
- configs.py
- const.py
- decoder.py
- f0_predictor.py
- flow.py
- flow_matching.py
- hifigan.py
- s3gen.py
- xvector.py
- __init__.cpython-310.pyc
- s3tokenizer.cpython-310.pyc
- __init__.py
- s3tokenizer.py
- __init__.cpython-310.pyc
- llama_configs.cpython-310.pyc
- t3.cpython-310.pyc
- alignment_stream_analyzer.cpython-310.pyc
- t3_hf_backend.cpython-310.pyc
- alignment_stream_analyzer.py
- t3_hf_backend.py
- cond_enc.cpython-310.pyc
- learned_pos_emb.cpython-310.pyc
- perceiver.cpython-310.pyc
- t3_config.cpython-310.pyc
- cond_enc.py
- learned_pos_emb.py
- perceiver.py
- t3_config.py
- __init__.py
- llama_configs.py
- t3.py
- __init__.cpython-310.pyc
- tokenizer.cpython-310.pyc
- __init__.py
- tokenizer.py
- __init__.cpython-310.pyc
- config.cpython-310.pyc
- melspec.cpython-310.pyc
- voice_encoder.cpython-310.pyc
- __init__.py
- config.py
- melspec.py
- voice_encoder.py
- utils.py
- __init__.py
- mtl_tts.py
- tts.py
- tts_turbo.py
- utils.py
- vc.py
- content_sequence.cpython-310.pyc
- tokenizer.cpython-310.pyc
- r_8_alpha_16.yaml
- base.yaml
- modded_dac_vq.yaml
- text2semantic_finetune.yaml
- en_US.json
- es_ES.json
- ja_JP.json
- ko_KR.json
- pt_BR.json
- zh_CN.json
- __init__.py
- core.py
- README.md
- scan.py
- __init__.cpython-310.pyc
- reference_loader.cpython-310.pyc
- utils.cpython-310.pyc
- vq_manager.cpython-310.pyc
- __init__.py
- reference_loader.py
- utils.py
- vq_manager.py
- __init__.cpython-310.pyc
- inference.cpython-310.pyc
- modded_dac.cpython-310.pyc
- rvq.cpython-310.pyc
- __init__.py
- inference.py
- modded_dac.py
- rvq.py
- __init__.cpython-310.pyc
- inference.cpython-310.pyc
- llama.cpython-310.pyc
- lora.cpython-310.pyc
- __init__.py
- inference.py
- lit_module.py
- llama.py
- lora.py
- __init__.cpython-310.pyc
- clean.cpython-310.pyc
- spliter.cpython-310.pyc
- __init__.py
- clean.py
- spliter.py
- __init__.cpython-310.pyc
- braceexpand.cpython-310.pyc
- context.cpython-310.pyc
- file.cpython-310.pyc
- instantiators.cpython-310.pyc
- logger.cpython-310.pyc
- logging_utils.cpython-310.pyc
- rich_utils.cpython-310.pyc
- schema.cpython-310.pyc
- utils.cpython-310.pyc
- __init__.py
- braceexpand.py
- context.py
- file.py
- instantiators.py
- logger.py
- logging_utils.py
- rich_utils.py
- schema.py
- spectrogram.py
- utils.py
- content_sequence.py
- tokenizer.py
- __init__.cpython-310.pyc
- constants.cpython-310.pyc
- data_types.cpython-310.pyc
- higgs_audio_tokenizer.cpython-310.pyc
- semantic_module.cpython-310.pyc
- __init__.cpython-310.pyc
- base.cpython-310.pyc
- dac.cpython-310.pyc
- base.py
- dac.py
- layers.py
- quantize.py
- __init__.py
- __init__.cpython-310.pyc
- core_vq_lsx_version.cpython-310.pyc
- ddp_utils.cpython-310.pyc
- distrib.cpython-310.pyc
- vq.cpython-310.pyc
- __init__.py
- ac.py
- core_vq.py
- core_vq_lsx_version.py
- ddp_utils.py
- distrib.py
- vq.py
- higgs_audio_tokenizer.py
- LICENSE
- semantic_module.py
- __init__.cpython-310.pyc
- higgs_audio_collator.cpython-310.pyc
- __init__.py
- higgs_audio_collator.py
- __init__.cpython-310.pyc
- chatml_dataset.cpython-310.pyc
- __init__.py
- chatml_dataset.py
- __init__.cpython-310.pyc
- audio_head.cpython-310.pyc
- common.cpython-310.pyc
- configuration_higgs_audio.cpython-310.pyc
- cuda_graph_runner.cpython-310.pyc
- custom_modules.cpython-310.pyc
- modeling_higgs_audio.cpython-310.pyc
- utils.cpython-310.pyc
- __init__.py
- audio_head.py
- common.py
- configuration_higgs_audio.py
- cuda_graph_runner.py
- custom_modules.py
- modeling_higgs_audio.py
- utils.py
- serve_engine.cpython-310.pyc
- serve_engine.py
- utils.py
- __init__.py
- constants.py
- data_types.py
- belinda.wav
- broom_salesman.wav
- chadwick.wav
- config.json
- en_man.wav
- en_woman.wav
- mabel.wav
- vex.wav
- zh_man_sichuan.wav
- __init__.cpython-310.pyc
- __init__.cpython-310.pyc
- infer.cpython-310.pyc
- __init__.cpython-310.pyc
- activations.cpython-310.pyc
- ECAPA_TDNN.cpython-310.pyc
- env.cpython-310.pyc
- models.cpython-310.pyc
- utils.cpython-310.pyc
- .gitignore
- __init__.py
- activation1d.py
- anti_alias_activation.cpp
- anti_alias_activation_cuda.cu
- compat.h
- load.py
- type_shim.h
- __init__.py
- act.py
- filter.py
- resample.py
- __init__.py
- __init__.cpython-310.pyc
- act.cpython-310.pyc
- filter.cpython-310.pyc
- resample.cpython-310.pyc
- __init__.py
- act.py
- filter.py
- resample.py
- __init__.cpython-310.pyc
- CNN.cpython-310.pyc
- linear.cpython-310.pyc
- normalization.cpython-310.pyc
- __init__.py
- CNN.py
- linear.py
- normalization.py
- __init__.py
- activations.py
- bigvgan.py
- ECAPA_TDNN.py
- env.py
- models.py
- utils.py
- __init__.cpython-310.pyc
- conformer_encoder.cpython-310.pyc
- model.cpython-310.pyc
- perceiver.cpython-310.pyc
- __init__.cpython-310.pyc
- attention.cpython-310.pyc
- embedding.cpython-310.pyc
- subsampling.cpython-310.pyc
- __init__.py
- attention.py
- embedding.py
- subsampling.py
- __init__.py
- conformer_encoder.py
- model.py
- perceiver.py
- __init__.cpython-310.pyc
- arch_util.cpython-310.pyc
- checkpoint.cpython-310.pyc
- common.cpython-310.pyc
- feature_extractors.cpython-310.pyc
- front.cpython-310.pyc
- typical_sampling.cpython-310.pyc
- xtransformers.cpython-310.pyc
- __init__.py
- arch_util.py
- checkpoint.py
- common.py
- feature_extractors.py
- front.py
- typical_sampling.py
- webui_utils.py
- xtransformers.py
- __init__.py
- xtts_dvae.py
- __init__.py
- cli.py
- infer.py
- __init__.py
- img.png
- index_icon.png
- IndexTTS.png
- config.yaml
- cases.jsonl
- emo_hate.wav
- emo_sad.wav
- voice_01.wav
- voice_02.wav
- voice_03.wav
- voice_04.wav
- voice_05.wav
- voice_06.wav
- voice_07.wav
- voice_08.wav
- voice_09.wav
- voice_10.wav
- voice_11.wav
- voice_12.wav
- .gitignore
- __init__.py
- activation1d.py
- anti_alias_activation.cpp
- anti_alias_activation_cuda.cu
- compat.h
- load.py
- type_shim.h
- __init__.py
- act.py
- filter.py
- resample.py
- __init__.py
- __init__.py
- act.py
- filter.py
- resample.py
- __init__.py
- CNN.py
- linear.py
- normalization.py
- __init__.py
- activations.py
- bigvgan.py
- ECAPA_TDNN.py
- models.py
- utils.py
- __init__.py
- attention.py
- embedding.py
- subsampling.py
- __init__.py
- conformer_encoder.py
- model.py
- model_v2.py
- perceiver.py
- transformers_beam_search.py
- transformers_generation_utils.py
- transformers_gpt2.py
- transformers_modeling_utils.py
- __init__.py
- base.py
- dac.py
- discriminator.py
- encodec.py
- __init__.py
- layers.py
- loss.py
- quantize.py
- __init__.py
- decode.py
- encode.py
- __init__.py
- __main__.py
- audio-checkpoint.py
- commons-checkpoint.py
- diffusion_transformer-checkpoint.py
- flow_matching-checkpoint.py
- length_regulator-checkpoint.py
- __init__.py
- act.py
- filter.py
- resample.py
- __init__.py
- activation1d.py
- anti_alias_activation.cpp
- anti_alias_activation_cuda.cu
- compat.h
- load.py
- type_shim.h
- __init__.py
- act.py
- filter.py
- resample.py
- activations.py
- bigvgan.py
- config.json
- env.py
- meldataset.py
- utils.py
- classifier.py
- DTDNN.py
- layers.py
- model-checkpoint.py
- generate.py
- model.py
- quantize.py
- f0_predictor.py
- generator.py
- config.json
- __init__.py
- api.py
- attentions.py
- commons.py
- mel_processing.py
- models.py
- modules.py
- openvoice_app.py
- se_extractor.py
- transforms.py
- utils.py
- __init__.py
- heads.py
- helpers.py
- loss.py
- models.py
- modules.py
- pretrained.py
- spectral_ops.py
- audio.py
- commons.py
- diffusion_transformer.py
- encodec.py
- flow_matching.py
- layers.py
- length_regulator.py
- quantize.py
- rmvpe.py
- wavenet.py
- hf_utils.py
- optimizers.py
- wav2vecbert_extract.py
- __init__.py
- factorized_vector_quantize.py
- lookup_free_quantize.py
- residual_vq.py
- vector_quantize.py
- codec.py
- vocos.py
- __init__.py
- act.py
- filter.py
- resample.py
- __init__.py
- bst.t7
- model.py
- attentions.py
- commons.py
- gradient_reversal.py
- layers.py
- quantize.py
- style_encoder.py
- wavenet.py
- __init__.py
- facodec_dataset.py
- facodec_inference.py
- facodec_trainer.py
- optimizer.py
- repcodec_model.py
- vocos.py
- melspec.py
- __init__.py
- act.py
- filter.py
- resample.py
- __init__.py
- fvq.py
- rvq.py
- __init__.py
- facodec.py
- gradient_reversal.py
- melspec.py
- README.md
- transformer.py
- __init__.py
- ac.py
- core_vq.py
- distrib.py
- vq.py
- __init__.py
- conv.py
- lstm.py
- norm.py
- seanet.py
- model.py
- vevo_repcodec.py
- __init__.py
- codec_dataset.py
- codec_inference.py
- codec_sampler.py
- codec_trainer.py
- wav2vec2bert_stats.pt
- llama_nar.py
- maskgct_s2a.py
- __init__.py
- arch_util.py
- checkpoint.py
- common.py
- feature_extractors.py
- front.py
- maskgct_utils.py
- text_utils.py
- typical_sampling.py
- utils.py
- webui_utils.py
- xtransformers.py
- __init__.py
- xtts_dvae.py
- __init__.py
- cli.py
- infer.py
- infer_v2.py
- cases.jsonl
- padding_test.py
- regression_test.py
- sample_prompt.wav
- en_US.json
- zh_CN.json
- i18n.py
- scan_i18n.py
- gpu_check.py
- .gitignore
- DISCLAIMER
- INDEX_MODEL_LICENSE
- LICENSE
- README.md
- requirements.txt
- setup.py
- webui.py
- __init__.cpython-310.pyc
- compat.cpython-310.pyc
- demo.py
- __init__.cpython-310.pyc
- __init__.cpython-310.pyc
- configuration_qwen3_tts.cpython-310.pyc
- modeling_qwen3_tts.cpython-310.pyc
- processing_qwen3_tts.cpython-310.pyc
- __init__.py
- configuration_qwen3_tts.py
- modeling_qwen3_tts.py
- processing_qwen3_tts.py
- configuration_qwen3_tts_tokenizer_v2.cpython-310.pyc
- modeling_qwen3_tts_tokenizer_v2.cpython-310.pyc
- configuration_qwen3_tts_tokenizer_v2.py
- modeling_qwen3_tts_tokenizer_v2.py
- configuration_qwen3_tts_tokenizer_v1.cpython-310.pyc
- modeling_qwen3_tts_tokenizer_v1.cpython-310.pyc
- core_vq.cpython-310.pyc
- speech_vq.cpython-310.pyc
- whisper_encoder.cpython-310.pyc
- mel_filters.npz
- core_vq.py
- speech_vq.py
- whisper_encoder.py
- configuration_qwen3_tts_tokenizer_v1.py
- modeling_qwen3_tts_tokenizer_v1.py
- __init__.py
- qwen3_tts_model.cpython-310.pyc
- qwen3_tts_tokenizer.cpython-310.pyc
- qwen3_tts_model.py
- qwen3_tts_tokenizer.py
- __init__.py
- __main__.py
- compat.py
- Sample.wav
- quantize.py
- api_utils.py
- exception_handler.py
- inference.py
- model_manager.py
- model_utils.py
- views.py
- create_train_split.py
- extract_vq.py
- __init__.py
- audio_effects.py
- inference.py
- variables.py
- api_client.py
- api_server.py
- download_indextts_models.py
- download_models.py
- run_webui.py
- smart_pad.py
- whisper_asr.py
- 1p_EN2CH.mp4
- 2p_see_u_again.mp4
- 4p_climate_45min.mp4
- 1p_abs.txt
- 1p_Ch2EN.txt
- 2p_goat.txt
- 2p_music.txt
- 2p_short.txt
- 2p_yayi.txt
- 3p_gpt5.txt
- 4p_climate_100min.txt
- 4p_climate_45min.txt
- custom-santa.wav
- en-Alice_woman.wav
- en-Carter_man.wav
- en-Frank_man.wav
- en-Mary_woman_bgm.wav
- en-Maya_woman.wav
- in-Samuel_man.wav
- zh-Anchen_man_bgm.wav
- zh-Bowen_man.wav
- zh-Xinran_woman.wav
- gradio_demo.py
- inference_from_file.py
- MODEL_DOWNLOAD_GUIDE.md
- test_download.py
- VibeVoice_colab.ipynb
- Google_AI_Studio_2025-08-25T21_48_13.452Z.png
- MOS-preference.png
- VibeVoice.jpg
- VibeVoice_logo.png
- VibeVoice_logo_white.png
- qwen2.5_1.5b_64k.json
- qwen2.5_7b_32k.json
- __init__.py
- configuration_vibevoice.py
- modeling_vibevoice.py
- modeling_vibevoice_inference.py
- modular_vibevoice_diffusion_head.py
- modular_vibevoice_text_tokenizer.py
- modular_vibevoice_tokenizer.py
- streamer.py
- __init__.py
- vibevoice_processor.py
- vibevoice_tokenizer_processor.py
- __init__.py
- dpm_solver.py
- timestep_sampler.py
- __init__.py
- convert_nnscaler_checkpoint_to_transformers.py
- __init__.py
- dependency_links.txt
- PKG-INFO
- requires.txt
- SOURCES.txt
- top_level.txt
- .gitignore
- .project-root
- chatterbox_turbo_handler.py
- ebook_converter.py
- f5_tts_handler.py
- ffmpeg_env_config.py
- fish_speech_s2_handler.py
- higgs_audio_handler.py
- indextts2_handler.py
- install_direct.bat
- kitten_tts_handler.py
- launch.py
- qwen_tts_handler.py
- README.md
- requirements.txt
- RUN_APP.bat
- RUN_INSTALLER.bat
- RUN_UPDATER.bat
- update.bat
- vibevoice_handler.py
- voxcpm_handler.py
// repository documentation
Was this content helpful?
(0 ratings)