Skip to content
Audio

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 moreDetails
Architecture: 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)
Discuss Telegram 0 15

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.4 GB · ready files0.9 GB
  • FP8 / INT8recommendedweights 0.2 GB0.7 GB
  • 4-bitweights 0.1 GB0.6 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # tts-hub/yourtts
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download tts-hub/yourtts --local-dir ~/models/yourtts
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to yourtts
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of yourtts (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

tts-hub/yourtts
Author
tts-hub
Category
Audio
Released
Posted

On NeyroLearn

Hugging Face

150

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments