[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-931":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":46,"readmeContent":47,"aiSummary":48,"trendingCount":16,"starSnapshotCount":16,"syncStatus":49,"lastSyncTime":50,"discoverSource":51},931,"TTS","coqui-ai\u002FTTS","coqui-ai","🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production","http:\u002F\u002Fcoqui.ai",null,"Python",45539,6115,338,6,0,13,60,264,54,45,"Mozilla Public License 2.0",false,"dev",true,[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"deep-learning","glow-tts","hifigan","melgan","multi-speaker-tts","python","pytorch","speaker-encoder","speaker-encodings","speech","speech-synthesis","tacotron","text-to-speech","tts","tts-model","vocoder","voice-cloning","voice-conversion","voice-synthesis","2026-06-12 02:00:20","\n## 🐸Coqui.ai News\n- 📣 ⓍTTSv2 is here with 16 languages and better performance across the board.\n- 📣 ⓍTTS fine-tuning code is out. Check the [example recipes](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Ftree\u002Fdev\u002Frecipes\u002Fljspeech).\n- 📣 ⓍTTS can now stream with \u003C200ms latency.\n- 📣 ⓍTTS, our production TTS model that can speak 13 languages, is released [Blog Post](https:\u002F\u002Fcoqui.ai\u002Fblog\u002Ftts\u002Fopen_xtts), [Demo](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fcoqui\u002Fxtts), [Docs](https:\u002F\u002Ftts.readthedocs.io\u002Fen\u002Fdev\u002Fmodels\u002Fxtts.html)\n- 📣 [🐶Bark](https:\u002F\u002Fgithub.com\u002Fsuno-ai\u002Fbark) is now available for inference with unconstrained voice cloning. [Docs](https:\u002F\u002Ftts.readthedocs.io\u002Fen\u002Fdev\u002Fmodels\u002Fbark.html)\n- 📣 You can use [~1100 Fairseq models](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Ffairseq\u002Ftree\u002Fmain\u002Fexamples\u002Fmms) with 🐸TTS.\n- 📣 🐸TTS now supports 🐢Tortoise with faster inference. [Docs](https:\u002F\u002Ftts.readthedocs.io\u002Fen\u002Fdev\u002Fmodels\u002Ftortoise.html)\n\n\u003Cdiv align=\"center\">\n\u003Cimg src=\"https:\u002F\u002Fstatic.scarf.sh\u002Fa.png?x-pxid=cf317fe7-2188-4721-bc01-124bb5d5dbb2\" \u002F>\n\n## \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fcoqui-ai\u002FTTS\u002Fmain\u002Fimages\u002Fcoqui-log-green-TTS.png\" height=\"56\"\u002F>\n\n\n**🐸TTS is a library for advanced Text-to-Speech generation.**\n\n🚀 Pretrained models in +1100 languages.\n\n🛠️ Tools for training new models and fine-tuning existing models in any language.\n\n📚 Utilities for dataset analysis and curation.\n______________________________________________________________________\n\n[![Discord](https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1037326658807533628?color=%239B59B6&label=chat%20on%20discord)](https:\u002F\u002Fdiscord.gg\u002F5eXr5seRrv)\n[![License](\u003Chttps:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MPL%202.0-brightgreen.svg>)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMPL-2.0)\n[![PyPI version](https:\u002F\u002Fbadge.fury.io\u002Fpy\u002FTTS.svg)](https:\u002F\u002Fbadge.fury.io\u002Fpy\u002FTTS)\n[![Covenant](https:\u002F\u002Fcamo.githubusercontent.com\u002F7d620efaa3eac1c5b060ece5d6aacfcc8b81a74a04d05cd0398689c01c4463bb\u002F68747470733a2f2f696d672e736869656c64732e696f2f62616467652f436f6e7472696275746f72253230436f76656e616e742d76322e3025323061646f707465642d6666363962342e737667)](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Fblob\u002Fmaster\u002FCODE_OF_CONDUCT.md)\n[![Downloads](https:\u002F\u002Fpepy.tech\u002Fbadge\u002Ftts)](https:\u002F\u002Fpepy.tech\u002Fproject\u002Ftts)\n[![DOI](https:\u002F\u002Fzenodo.org\u002Fbadge\u002F265612440.svg)](https:\u002F\u002Fzenodo.org\u002Fbadge\u002Flatestdoi\u002F265612440)\n\n![GithubActions](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Factions\u002Fworkflows\u002Faux_tests.yml\u002Fbadge.svg)\n![GithubActions](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Factions\u002Fworkflows\u002Fdata_tests.yml\u002Fbadge.svg)\n![GithubActions](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Factions\u002Fworkflows\u002Fdocker.yaml\u002Fbadge.svg)\n![GithubActions](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Factions\u002Fworkflows\u002Finference_tests.yml\u002Fbadge.svg)\n![GithubActions](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Factions\u002Fworkflows\u002Fstyle_check.yml\u002Fbadge.svg)\n![GithubActions](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Factions\u002Fworkflows\u002Ftext_tests.yml\u002Fbadge.svg)\n![GithubActions](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Factions\u002Fworkflows\u002Ftts_tests.yml\u002Fbadge.svg)\n![GithubActions](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Factions\u002Fworkflows\u002Fvocoder_tests.yml\u002Fbadge.svg)\n![GithubActions](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Factions\u002Fworkflows\u002Fzoo_tests0.yml\u002Fbadge.svg)\n![GithubActions](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Factions\u002Fworkflows\u002Fzoo_tests1.yml\u002Fbadge.svg)\n![GithubActions](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Factions\u002Fworkflows\u002Fzoo_tests2.yml\u002Fbadge.svg)\n[![Docs](\u003Chttps:\u002F\u002Freadthedocs.org\u002Fprojects\u002Ftts\u002Fbadge\u002F?version=latest&style=plastic>)](https:\u002F\u002Ftts.readthedocs.io\u002Fen\u002Flatest\u002F)\n\n\u003C\u002Fdiv>\n\n______________________________________________________________________\n\n## 💬 Where to ask questions\nPlease use our dedicated channels for questions and discussion. Help is much more valuable if it's shared publicly so that more people can benefit from it.\n\n| Type                            | Platforms                               |\n| ------------------------------- | --------------------------------------- |\n| 🚨 **Bug Reports**              | [GitHub Issue Tracker]                  |\n| 🎁 **Feature Requests & Ideas** | [GitHub Issue Tracker]                  |\n| 👩‍💻 **Usage Questions**          | [GitHub Discussions]                    |\n| 🗯 **General Discussion**       | [GitHub Discussions] or [Discord]   |\n\n[github issue tracker]: https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002Ftts\u002Fissues\n[github discussions]: https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Fdiscussions\n[discord]: https:\u002F\u002Fdiscord.gg\u002F5eXr5seRrv\n[Tutorials and Examples]: https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Fwiki\u002FTTS-Notebooks-and-Tutorials\n\n\n## 🔗 Links and Resources\n| Type                            | Links                               |\n| ------------------------------- | --------------------------------------- |\n| 💼 **Documentation**              | [ReadTheDocs](https:\u002F\u002Ftts.readthedocs.io\u002Fen\u002Flatest\u002F)\n| 💾 **Installation**               | [TTS\u002FREADME.md](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Ftree\u002Fdev#installation)|\n| 👩‍💻 **Contributing**               | [CONTRIBUTING.md](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Fblob\u002Fmain\u002FCONTRIBUTING.md)|\n| 📌 **Road Map**                   | [Main Development Plans](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Fissues\u002F378)\n| 🚀 **Released Models**            | [TTS Releases](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Freleases) and [Experimental Models](https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\u002Fwiki\u002FExperimental-Released-Models)|\n| 📰 **Papers**                    | [TTS Papers](https:\u002F\u002Fgithub.com\u002Ferogol\u002FTTS-papers)|\n\n\n## 🥇 TTS Performance\n\u003Cp align=\"center\">\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fcoqui-ai\u002FTTS\u002Fmain\u002Fimages\u002FTTS-performance.png\" width=\"800\" \u002F>\u003C\u002Fp>\n\nUnderlined \"TTS*\" and \"Judy*\" are **internal** 🐸TTS models that are not released open-source. They are here to show the potential. Models prefixed with a dot (.Jofish .Abe and .Janice) are real human voices.\n\n## Features\n- High-performance Deep Learning models for Text2Speech tasks.\n    - Text2Spec models (Tacotron, Tacotron2, Glow-TTS, SpeedySpeech).\n    - Speaker Encoder to compute speaker embeddings efficiently.\n    - Vocoder models (MelGAN, Multiband-MelGAN, GAN-TTS, ParallelWaveGAN, WaveGrad, WaveRNN)\n- Fast and efficient model training.\n- Detailed training logs on the terminal and Tensorboard.\n- Support for Multi-speaker TTS.\n- Efficient, flexible, lightweight but feature complete `Trainer API`.\n- Released and ready-to-use models.\n- Tools to curate Text2Speech datasets under```dataset_analysis```.\n- Utilities to use and test your models.\n- Modular (but not too much) code base enabling easy implementation of new ideas.\n\n## Model Implementations\n### Spectrogram models\n- Tacotron: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1703.10135)\n- Tacotron2: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.05884)\n- Glow-TTS: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.11129)\n- Speedy-Speech: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.03802)\n- Align-TTS: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.01950)\n- FastPitch: [paper](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.06873.pdf)\n- FastSpeech: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.09263)\n- FastSpeech2: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.04558)\n- SC-GlowTTS: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.05557)\n- Capacitron: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.03402)\n- OverFlow: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.06892)\n- Neural HMM TTS: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.13320)\n- Delightful TTS: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.12612)\n\n### End-to-End Models\n- ⓍTTS: [blog](https:\u002F\u002Fcoqui.ai\u002Fblog\u002Ftts\u002Fopen_xtts)\n- VITS: [paper](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.06103)\n- 🐸 YourTTS: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2112.02418)\n- 🐢 Tortoise: [orig. repo](https:\u002F\u002Fgithub.com\u002Fneonbjb\u002Ftortoise-tts)\n- 🐶 Bark: [orig. repo](https:\u002F\u002Fgithub.com\u002Fsuno-ai\u002Fbark)\n\n### Attention Methods\n- Guided Attention: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1710.08969)\n- Forward Backward Decoding: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1907.09006)\n- Graves Attention: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.10288)\n- Double Decoder Consistency: [blog](https:\u002F\u002Ferogol.com\u002Fsolving-attention-problems-of-tts-models-with-double-decoder-consistency\u002F)\n- Dynamic Convolutional Attention: [paper](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.10288.pdf)\n- Alignment Network: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.10447)\n\n### Speaker Encoder\n- GE2E: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1710.10467)\n- Angular Loss: [paper](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2003.11982.pdf)\n\n### Vocoders\n- MelGAN: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.06711)\n- MultiBandMelGAN: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.05106)\n- ParallelWaveGAN: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.11480)\n- GAN-TTS discriminators: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.11646)\n- WaveRNN: [origin](https:\u002F\u002Fgithub.com\u002Ffatchord\u002FWaveRNN\u002F)\n- WaveGrad: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.00713)\n- HiFiGAN: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.05646)\n- UnivNet: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.07889)\n\n### Voice Conversion\n- FreeVC: [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.15418)\n\nYou can also help us implement more models.\n\n## Installation\n🐸TTS is tested on Ubuntu 18.04 with **python >= 3.9, \u003C 3.12.**.\n\nIf you are only interested in [synthesizing speech](https:\u002F\u002Ftts.readthedocs.io\u002Fen\u002Flatest\u002Finference.html) with the released 🐸TTS models, installing from PyPI is the easiest option.\n\n```bash\npip install TTS\n```\n\nIf you plan to code or train models, clone 🐸TTS and install it locally.\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fcoqui-ai\u002FTTS\npip install -e .[all,dev,notebooks]  # Select the relevant extras\n```\n\nIf you are on Ubuntu (Debian), you can also run following commands for installation.\n\n```bash\n$ make system-deps  # intended to be used on Ubuntu (Debian). Let us know if you have a different OS.\n$ make install\n```\n\nIf you are on Windows, 👑@GuyPaddock wrote installation instructions [here](https:\u002F\u002Fstackoverflow.com\u002Fquestions\u002F66726331\u002Fhow-can-i-run-mozilla-tts-coqui-tts-training-with-cuda-on-a-windows-system).\n\n\n## Docker Image\nYou can also try TTS without install with the docker image.\nSimply run the following command and you will be able to run TTS without installing it.\n\n```bash\ndocker run --rm -it -p 5002:5002 --entrypoint \u002Fbin\u002Fbash ghcr.io\u002Fcoqui-ai\u002Ftts-cpu\npython3 TTS\u002Fserver\u002Fserver.py --list_models #To get the list of available models\npython3 TTS\u002Fserver\u002Fserver.py --model_name tts_models\u002Fen\u002Fvctk\u002Fvits # To start a server\n```\n\nYou can then enjoy the TTS server [here](http:\u002F\u002F[::1]:5002\u002F)\nMore details about the docker images (like GPU support) can be found [here](https:\u002F\u002Ftts.readthedocs.io\u002Fen\u002Flatest\u002Fdocker_images.html)\n\n\n## Synthesizing speech by 🐸TTS\n\n### 🐍 Python API\n\n#### Running a multi-speaker and multi-lingual model\n\n```python\nimport torch\nfrom TTS.api import TTS\n\n# Get device\ndevice = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n\n# List available 🐸TTS models\nprint(TTS().list_models())\n\n# Init TTS\ntts = TTS(\"tts_models\u002Fmultilingual\u002Fmulti-dataset\u002Fxtts_v2\").to(device)\n\n# Run TTS\n# ❗ Since this model is multi-lingual voice cloning model, we must set the target speaker_wav and language\n# Text to speech list of amplitude values as output\nwav = tts.tts(text=\"Hello world!\", speaker_wav=\"my\u002Fcloning\u002Faudio.wav\", language=\"en\")\n# Text to speech to a file\ntts.tts_to_file(text=\"Hello world!\", speaker_wav=\"my\u002Fcloning\u002Faudio.wav\", language=\"en\", file_path=\"output.wav\")\n```\n\n#### Running a single speaker model\n\n```python\n# Init TTS with the target model name\ntts = TTS(model_name=\"tts_models\u002Fde\u002Fthorsten\u002Ftacotron2-DDC\", progress_bar=False).to(device)\n\n# Run TTS\ntts.tts_to_file(text=\"Ich bin eine Testnachricht.\", file_path=OUTPUT_PATH)\n\n# Example voice cloning with YourTTS in English, French and Portuguese\ntts = TTS(model_name=\"tts_models\u002Fmultilingual\u002Fmulti-dataset\u002Fyour_tts\", progress_bar=False).to(device)\ntts.tts_to_file(\"This is voice cloning.\", speaker_wav=\"my\u002Fcloning\u002Faudio.wav\", language=\"en\", file_path=\"output.wav\")\ntts.tts_to_file(\"C'est le clonage de la voix.\", speaker_wav=\"my\u002Fcloning\u002Faudio.wav\", language=\"fr-fr\", file_path=\"output.wav\")\ntts.tts_to_file(\"Isso é clonagem de voz.\", speaker_wav=\"my\u002Fcloning\u002Faudio.wav\", language=\"pt-br\", file_path=\"output.wav\")\n```\n\n#### Example voice conversion\n\nConverting the voice in `source_wav` to the voice of `target_wav`\n\n```python\ntts = TTS(model_name=\"voice_conversion_models\u002Fmultilingual\u002Fvctk\u002Ffreevc24\", progress_bar=False).to(\"cuda\")\ntts.voice_conversion_to_file(source_wav=\"my\u002Fsource.wav\", target_wav=\"my\u002Ftarget.wav\", file_path=\"output.wav\")\n```\n\n#### Example voice cloning together with the voice conversion model.\nThis way, you can clone voices by using any model in 🐸TTS.\n\n```python\n\ntts = TTS(\"tts_models\u002Fde\u002Fthorsten\u002Ftacotron2-DDC\")\ntts.tts_with_vc_to_file(\n    \"Wie sage ich auf Italienisch, dass ich dich liebe?\",\n    speaker_wav=\"target\u002Fspeaker.wav\",\n    file_path=\"output.wav\"\n)\n```\n\n#### Example text to speech using **Fairseq models in ~1100 languages** 🤯.\nFor Fairseq models, use the following name format: `tts_models\u002F\u003Clang-iso_code>\u002Ffairseq\u002Fvits`.\nYou can find the language ISO codes [here](https:\u002F\u002Fdl.fbaipublicfiles.com\u002Fmms\u002Ftts\u002Fall-tts-languages.html)\nand learn about the Fairseq models [here](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Ffairseq\u002Ftree\u002Fmain\u002Fexamples\u002Fmms).\n\n```python\n# TTS with on the fly voice conversion\napi = TTS(\"tts_models\u002Fdeu\u002Ffairseq\u002Fvits\")\napi.tts_with_vc_to_file(\n    \"Wie sage ich auf Italienisch, dass ich dich liebe?\",\n    speaker_wav=\"target\u002Fspeaker.wav\",\n    file_path=\"output.wav\"\n)\n```\n\n### Command-line `tts`\n\n\u003C!-- begin-tts-readme -->\n\nSynthesize speech on command line.\n\nYou can either use your trained model or choose a model from the provided list.\n\nIf you don't specify any models, then it uses LJSpeech based English model.\n\n#### Single Speaker Models\n\n- List provided models:\n\n  ```\n  $ tts --list_models\n  ```\n\n- Get model info (for both tts_models and vocoder_models):\n\n  - Query by type\u002Fname:\n    The model_info_by_name uses the name as it from the --list_models.\n    ```\n    $ tts --model_info_by_name \"\u003Cmodel_type>\u002F\u003Clanguage>\u002F\u003Cdataset>\u002F\u003Cmodel_name>\"\n    ```\n    For example:\n    ```\n    $ tts --model_info_by_name tts_models\u002Ftr\u002Fcommon-voice\u002Fglow-tts\n    $ tts --model_info_by_name vocoder_models\u002Fen\u002Fljspeech\u002Fhifigan_v2\n    ```\n  - Query by type\u002Fidx:\n    The model_query_idx uses the corresponding idx from --list_models.\n\n    ```\n    $ tts --model_info_by_idx \"\u003Cmodel_type>\u002F\u003Cmodel_query_idx>\"\n    ```\n\n    For example:\n\n    ```\n    $ tts --model_info_by_idx tts_models\u002F3\n    ```\n\n  - Query info for model info by full name:\n    ```\n    $ tts --model_info_by_name \"\u003Cmodel_type>\u002F\u003Clanguage>\u002F\u003Cdataset>\u002F\u003Cmodel_name>\"\n    ```\n\n- Run TTS with default models:\n\n  ```\n  $ tts --text \"Text for TTS\" --out_path output\u002Fpath\u002Fspeech.wav\n  ```\n\n- Run TTS and pipe out the generated TTS wav file data:\n\n  ```\n  $ tts --text \"Text for TTS\" --pipe_out --out_path output\u002Fpath\u002Fspeech.wav | aplay\n  ```\n\n- Run a TTS model with its default vocoder model:\n\n  ```\n  $ tts --text \"Text for TTS\" --model_name \"\u003Cmodel_type>\u002F\u003Clanguage>\u002F\u003Cdataset>\u002F\u003Cmodel_name>\" --out_path output\u002Fpath\u002Fspeech.wav\n  ```\n\n  For example:\n\n  ```\n  $ tts --text \"Text for TTS\" --model_name \"tts_models\u002Fen\u002Fljspeech\u002Fglow-tts\" --out_path output\u002Fpath\u002Fspeech.wav\n  ```\n\n- Run with specific TTS and vocoder models from the list:\n\n  ```\n  $ tts --text \"Text for TTS\" --model_name \"\u003Cmodel_type>\u002F\u003Clanguage>\u002F\u003Cdataset>\u002F\u003Cmodel_name>\" --vocoder_name \"\u003Cmodel_type>\u002F\u003Clanguage>\u002F\u003Cdataset>\u002F\u003Cmodel_name>\" --out_path output\u002Fpath\u002Fspeech.wav\n  ```\n\n  For example:\n\n  ```\n  $ tts --text \"Text for TTS\" --model_name \"tts_models\u002Fen\u002Fljspeech\u002Fglow-tts\" --vocoder_name \"vocoder_models\u002Fen\u002Fljspeech\u002Funivnet\" --out_path output\u002Fpath\u002Fspeech.wav\n  ```\n\n- Run your own TTS model (Using Griffin-Lim Vocoder):\n\n  ```\n  $ tts --text \"Text for TTS\" --model_path path\u002Fto\u002Fmodel.pth --config_path path\u002Fto\u002Fconfig.json --out_path output\u002Fpath\u002Fspeech.wav\n  ```\n\n- Run your own TTS and Vocoder models:\n\n  ```\n  $ tts --text \"Text for TTS\" --model_path path\u002Fto\u002Fmodel.pth --config_path path\u002Fto\u002Fconfig.json --out_path output\u002Fpath\u002Fspeech.wav\n      --vocoder_path path\u002Fto\u002Fvocoder.pth --vocoder_config_path path\u002Fto\u002Fvocoder_config.json\n  ```\n\n#### Multi-speaker Models\n\n- List the available speakers and choose a \u003Cspeaker_id> among them:\n\n  ```\n  $ tts --model_name \"\u003Clanguage>\u002F\u003Cdataset>\u002F\u003Cmodel_name>\"  --list_speaker_idxs\n  ```\n\n- Run the multi-speaker TTS model with the target speaker ID:\n\n  ```\n  $ tts --text \"Text for TTS.\" --out_path output\u002Fpath\u002Fspeech.wav --model_name \"\u003Clanguage>\u002F\u003Cdataset>\u002F\u003Cmodel_name>\"  --speaker_idx \u003Cspeaker_id>\n  ```\n\n- Run your own multi-speaker TTS model:\n\n  ```\n  $ tts --text \"Text for TTS\" --out_path output\u002Fpath\u002Fspeech.wav --model_path path\u002Fto\u002Fmodel.pth --config_path path\u002Fto\u002Fconfig.json --speakers_file_path path\u002Fto\u002Fspeaker.json --speaker_idx \u003Cspeaker_id>\n  ```\n\n### Voice Conversion Models\n\n```\n$ tts --out_path output\u002Fpath\u002Fspeech.wav --model_name \"\u003Clanguage>\u002F\u003Cdataset>\u002F\u003Cmodel_name>\" --source_wav \u003Cpath\u002Fto\u002Fspeaker\u002Fwav> --target_wav \u003Cpath\u002Fto\u002Freference\u002Fwav>\n```\n\n\u003C!-- end-tts-readme -->\n\n## Directory Structure\n```\n|- notebooks\u002F       (Jupyter Notebooks for model evaluation, parameter selection and data analysis.)\n|- utils\u002F           (common utilities.)\n|- TTS\n    |- bin\u002F             (folder for all the executables.)\n      |- train*.py                  (train your target model.)\n      |- ...\n    |- tts\u002F             (text to speech models)\n        |- layers\u002F          (model layer definitions)\n        |- models\u002F          (model definitions)\n        |- utils\u002F           (model specific utilities.)\n    |- speaker_encoder\u002F (Speaker Encoder models.)\n        |- (same)\n    |- vocoder\u002F         (Vocoder models.)\n        |- (same)\n```\n","Coqui TTS 是一个基于深度学习的文本转语音工具包，已在研究和生产环境中得到验证。该项目支持超过1100种语言的预训练模型，并提供工具用于训练新模型及对现有模型进行微调。其核心技术包括Glow-TTS、HiFiGAN等先进的声码器与多说话人TTS模型，能够实现高质量语音合成、实时流式传输（延迟低于200毫秒）以及无限制的声音克隆等功能。适用于需要自然流畅语音输出的各种应用场景，如虚拟助手、有声读物制作、在线教育平台等。",2,"2026-06-11 02:40:19","top_all"]