WebUI Extension Marketplace

Extensions List shows the list of interface extensions in the web UI

Decorator Extensions List shows the list of decorator extensions in the web UI

Gradio Settings allows to configure Gradio interface options from the web UI

Display GPU information such as VRAM, CUDA version, and more.

Pip List shows the list of installed packages in the web UI

Model Location Settings allows changing the location of the model cache directories used by Hugging Face and Torch Hub.

Add external extension entries via JSON and install them without restarts.

View, search, and manage log files from the TTS Generation WebUI. Browse installation logs, filter by keywords, and clean up old logs.

Multilingual text-to-speech model supporting English, Chinese, and Japanese

StyleTTS2 is a text-to-speech model that generates high-quality speech with controllable style

SeamlessM4T is a multilingual and multimodal translation model supporting text and speech

MMS (Massively Multilingual Speech) is a text-to-speech model supporting over 1000 languages

Tortoise TTS is a high-quality text-to-speech model with voice cloning capabilities

F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching.

Chatterbox, Resemble AI's first production-grade open source TTS model

Kokoro: A small, fast, and high-quality TTS model

Bark: A text-to-speech model

XTTS-Simple is a Gradio UI for XTTSv2

Parler-TTS is a training and inference library for high-fidelity text-to-speech (TTS) models.

CosyVoice: High-quality text-to-speech synthesis.

MARS5: A novel speech model for insane prosody

DIA: A text-to-dialogue model

GPT-SoVITS: A TTS solution powered by GPT and SoftVC VITS Singing Voice Conversion.

Maha TTS allows generating speech from text using the MahaTTS model.

OpenVoice: A versatile instant voice cloning approach

OpenVoice: A versatile instant voice cloning approach

Piper TTS is a text-to-speech model by rsxdalv

Higgs V2

A template extension for TTS Generation WebUI

A template extension for TTS Generation WebUI

A template extension for TTS Generation WebUI

A template extension for TTS Generation WebUI

A template extension for TTS Generation WebUI

A template extension for TTS Generation WebUI

ACE-Step: A Step Towards Music Generation Foundation Model

Stable Audio is a text-to-audio model for generating high-quality music and sound effects

Audiocraft provides MusicGen and MAGNeT models for high-quality music and audio generation

AudioCraft Plus is an all-in-one WebUI for the original AudioCraft, adding many quality features on top.

Riffusion allows generating music from text.

MusicGen allows generating music from text

A template extension for TTS Generation WebUI

Vocos is a neural audio codec for high-quality audio compression and reconstruction

RVC: Retrieval-based Voice Conversion

Demucs is a music source separation model that can separate drums, bass, vocals, and other instruments

Audio Separator allows separating audio files into multiple audio files.

Resemble Enhance allows enhancing audio files.

AP-BWE: An audio bandwidth extension solution using Amplitude-Phase Bandwidth Extension models.

A template extension for TTS Generation WebUI

Outputs Tab for TTS WebUI

Gallery History allows selecting previously generated audio files by looking at their waveforms

FFMPEG Metadata allows loading metadata from audio files.

OpenAI compatible TTS API with support for multiple TTS models

Whisper allows transcribing audio files.

XTTS fine-tuning demo

Huggingface Cache Manager allows managing the Huggingface cache.

Model Downloader allows downloading models from the Huggingface model hub.

Simple remixer allows concatenating multiple audio files and mixing them together.

Conda Storage Optimizer allows cleaning up conda storage to free disk space.

RVC Training

Bark Voice Clone allows cloning voices for use with Bark TTS

Ebook2Audiobook allows converting ebooks to audiobooks

EPub2TTS allows converting ebooks to audiobooks

Audiobook Generator allows converting ebooks to audiobooks

CUDA Toolkit

Kimi Audio is a powerful text-to-speech and speech-to-text model by Moonshot AI

A template extension for TTS Generation WebUI

YouTube Tutorials shows a list of YouTube tutorials in the web UI

Speech transcription via Nvidia Parakeet model

This is the legacy UI of Bark from TTS-WebUI

PyVideoTrans text-to-speech API with WebUI integration.

Import and parse multiple SRT files into JSON segments for later TTS batching.

Install and uninstall Python packages from the web UI. Disable when not in use for security.

Decorator Save Ogg

Decorator Save Waveform

Decorator Average Execution Time