coqui-ai/TTS

What it is

🐸TTS is a library for advanced Text-to-Speech generation. It provides pretrained models in over 1100 languages, tools for training and fine-tuning models in any language, and utilities for dataset analysis and curation. It includes spectrogram models, end-to-end models such as ⓍTTS, VITS, YourTTS, Tortoise and Bark, vocoders, a speaker encoder, and voice conversion.

Who it's for

• Developers who want to synthesize speech from released pretrained TTS models via Python or the command line
• Researchers and engineers training or fine-tuning TTS models in any language
• Users who need multi-speaker, multilingual or voice-cloning TTS
• People curating Text2Speech datasets

Requirements

Setup

1. Install from PyPI (synthesis only)

   The easiest option if you only want to synthesize speech with the released models.

   bashCopy

   pip install TTS

2. Install locally for coding or training

   Clone the repo and install it locally, selecting the relevant extras.

   bashCopy

   git clone https://github.com/coqui-ai/TTS
   pip install -e .[all,dev,notebooks]  # Select the relevant extras

3. Ubuntu/Debian install via make

   On Ubuntu (Debian) you can also use these commands.

   bashCopy

   $ make system-deps  # intended to be used on Ubuntu (Debian). Let us know if you have a different OS.
   $ make install

4. Try with Docker

   Run TTS without installing it by using the CPU docker image, then start a server.

   bashCopy

   docker run --rm -it -p 5002:5002 --entrypoint /bin/bash ghcr.io/coqui-ai/tts-cpu
   python3 TTS/server/server.py --list_models #To get the list of available models
   python3 TTS/server/server.py --model_name tts_models/en/vctk/vits # To start a server

Examples

import torch
from TTS.api import TTS

# Get device
device = "cuda" if torch.cuda.is_available() else "cpu"

# List available 🐸TTS models
print(TTS().list_models())

# Init TTS
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to(device)

wav = tts.tts(text="Hello world!", speaker_wav="my/cloning/audio.wav", language="en")
tts.tts_to_file(text="Hello world!", speaker_wav="my/cloning/audio.wav", language="en", file_path="output.wav")

tts = TTS(model_name="voice_conversion_models/multilingual/vctk/freevc24", progress_bar=False).to("cuda")
tts.voice_conversion_to_file(source_wav="my/source.wav", target_wav="my/target.wav", file_path="output.wav")

tts = TTS("tts_models/de/thorsten/tacotron2-DDC")
tts.tts_with_vc_to_file(
    "Wie sage ich auf Italienisch, dass ich dich liebe?",
    speaker_wav="target/speaker.wav",
    file_path="output.wav"
)

$ tts --text "Text for TTS" --model_name "tts_models/en/ljspeech/glow-tts" --out_path output/path/speech.wav

$ tts --list_models

Pros & cons

Images