phoonnx-coqui-vits

Mirror of the Coqui TTS project's community VITS checkpoints, exported to ONNX for phoonnx, OpenVoiceOS's offline TTS library. These are the single-speaker and multi-speaker VITS models that shipped in Coqui TTS's own model zoo (.models.json), trained on Common Voice, CSS10, M-AILABS, and OpenBible/Bloom-Library corpora, covering 34 languages from Bulgarian to Yoruba.

This repository holds the raw ONNX weights and config.json files consumed by phoonnx's voice_index (coqui_vits.json); it is not meant to be browsed for voices directly โ€” use phoonnx's voice manager, which resolves voice IDs to the files here.

Usage

import wave
from phoonnx.model_manager import TTSModelManager

manager = TTSModelManager()
manager.load()
manager.merge_default_voices()

voice = manager.voices["coqui/de-thorsten-vits"].load()
with wave.open("out.wav", "wb") as wav_file:
    voice.synthesize_wav("Guten Tag, wie geht es dir?", wav_file)

License

license: other because each checkpoint carries the license Coqui TTS assigned it in its own .models.json at the time of training โ€” these differ per corpus and are not uniform. Below is every voice in this repository with the license recorded by upstream Coqui TTS.

Voice ID Directory Language Corpus License
coqui/bg-cv-vits bg-cv-vits bg-BG Common Voice BSD-3-Clause
coqui/bn-custom-vits-male bn-custom-vits-male bn custom Apache-2.0
coqui/ca-custom-vits ca-custom-vits ca custom CC-BY-4.0
coqui/cs-cv-vits cs-cv-vits cs-CZ Common Voice BSD-3-Clause
coqui/da-cv-vits da-cv-vits da-DK Common Voice BSD-3-Clause
coqui/de-thorsten-vits de-thorsten-vits de Thorsten Apache-2.0
coqui/el-cv-vits el-cv-vits el-GR Common Voice BSD-3-Clause
coqui/en-ljspeech-vits en-ljspeech-vits en-US LJSpeech Apache-2.0
coqui/en-vctk-vits en-vctk-vits en-US VCTK Apache-2.0
coqui/es-css10-vits es-css10-vits es CSS10 BSD-3-Clause
coqui/et-cv-vits et-cv-vits et-EE Common Voice BSD-3-Clause
coqui/ewe-openbible-vits ewe-openbible-vits ee OpenBible CC-BY-SA-4.0
coqui/fa-custom-vits-female fa-custom-vits-female fa custom CC-BY-4.0
coqui/fi-css10-vits fi-css10-vits fi-FI CSS10 BSD-3-Clause
coqui/fr-css10-vits fr-css10-vits fr CSS10 BSD-3-Clause
coqui/ga-cv-vits ga-cv-vits ga-IE Common Voice BSD-3-Clause
coqui/hau-openbible-vits hau-openbible-vits ha OpenBible CC-BY-SA-4.0
coqui/hr-cv-vits hr-cv-vits hr-HR Common Voice BSD-3-Clause
coqui/hu-css10-vits hu-css10-vits hu-HU CSS10 BSD-3-Clause
coqui/it-mai_female-vits it-mai_female-vits it M-AILABS Apache-2.0
coqui/it-mai_male-vits it-mai_male-vits it M-AILABS Apache-2.0
coqui/lin-openbible-vits lin-openbible-vits ln OpenBible CC-BY-SA-4.0
coqui/lt-cv-vits lt-cv-vits lt-LT Common Voice BSD-3-Clause
coqui/lv-cv-vits lv-cv-vits lv-LV Common Voice BSD-3-Clause
coqui/mt-cv-vits mt-cv-vits mt-MT Common Voice BSD-3-Clause
coqui/nl-css10-vits nl-css10-vits nl CSS10 BSD-3-Clause
coqui/pl-mai_female-vits pl-mai_female-vits pl-PL M-AILABS BSD-3-Clause
coqui/pt-cv-vits pt-cv-vits pt Common Voice BSD-3-Clause
coqui/ro-cv-vits ro-cv-vits ro-RO Common Voice BSD-3-Clause
coqui/sk-cv-vits sk-cv-vits sk-SK Common Voice BSD-3-Clause
coqui/sl-cv-vits sl-cv-vits sl-SI Common Voice BSD-3-Clause
coqui/sv-cv-vits sv-cv-vits sv Common Voice BSD-3-Clause
coqui/tw_akuapem-openbible-vits tw_akuapem-openbible-vits tw-GH OpenBible CC-BY-SA-4.0
coqui/tw_asante-openbible-vits tw_asante-openbible-vits tw-GH OpenBible CC-BY-SA-4.0
coqui/uk-mai-vits uk-mai-vits uk-UA M-AILABS BSD-3-Clause
coqui/yor-openbible-vits yor-openbible-vits yo OpenBible CC-BY-SA-4.0

Licenses are as recorded in the upstream coqui-ai/TTS .models.json at the time these checkpoints were exported; phoonnx itself is Apache-2.0.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Collection including OpenVoiceOS/phoonnx-coqui-vits