YourTTS
multilingual text-to-speech and voice cloning model
2 min readupdated
Built on the VITS architecture, YourTTS supports English, French, and Brazilian Portuguese. It lets you clone a voice from a short audio clip (zero-shot) or use built-in speakers. The checkpoint is adapted for the coqui-tts library and includes fixed paths to the speaker encoder and speaker config file. The model works well for voice assistants, content localization, and voiceovers in the supported languages.
Key features
- Zero-shot voice cloning from a few seconds of reference audio
- Supports three languages: English, French, and Brazilian Portuguese
- Built on the VITS architecture with language and external speaker embeddings
- Built-in speakers and support for plugging in an external encoder
What you can do
- Generate speech in English, French, or Portuguese using built-in speakers
- Clone any voice from a short, clean audio clip free of background noise
- Integrate speech synthesis into pipelines and apps using the coqui-tts library
Example
from TTS.api import TTS
tts = TTS("tts_models/multilingual/multi-dataset/your_tts")
tts.tts_to_file(
text="Ceci est un test de synthèse vocale.",
speaker_wav="reference.wav",
language="fr-fr",
file_path="output.wav",
)
Read more
DetailsArchitecture: YourTTS (VITS with language and external embeddings), 16 kHz output
Inputs: raw characters without a phonemizer, normalized via multilingual_cleaners
Limitations: character-based reading may mispronounce rare words and numbers; French and Portuguese were trained on a small number of speakers
License: CC BY-NC-ND 4.0 (non-commercial use only)










Comments