Danil Boldyrev

xtts-webui. Webui for using XTTS and for finetuning it

xtts-api-server. A simple FastAPI Server to run XTTSv2

xtts-finetune-webui. Slightly improved official version for finetune xtts

rvc-python. Using RVC via console or python scripts

mcpo-control-panel. Web UI and API for managing MCP Orchestrator (mcpo) instances and configurations

hallo-webui. Webui for Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

stable-diffusion-colab. Adapdet for google colab

resemble-enhance-windows. AI powered speech denoising and enhancement. Adapted for windows and optimized

deepspeed-windows-wheels. A collection of compiled wheels for deepspeed built for python 3.10 and 3.11 with support for cuda 11.8 and 12.1 for Windows

RVC-telegram-bot. Bot in Telegram that converts voice with rvc

silero-tts-enhanced. Silero TTS Enhanced is a Python library that enhances the original Silero TTS project, providing a convenient way to synthesize speech from text using Silero TTS models. It offers a user-friendly interface for both standalone script usage and integration into Python projects, along with additional features

Voyager_checkpoint. Checkpoint for Voyager, 160 iterations.

silero-rvc-tts-ru-gui. Комбинация технологии silero-tts и rvc для создания любого голоса для tts

xtts-finetune-tests. In this repository I will be running various experiments on finetune different parts for xtts

wd14-tagger-api-server. FastApi server for WD Tagger 1.4

xformers_prebuild_wheels. xformers prebuild wheels for various video cards, suitable for both paperspace and google colab

openvoice-cli. Instant voice cloning by MyShell. Via the console

posex. Posex - Estimated Image Generator for Pose2Image

FollowYourEmoji-Webui. Google collab version for Follow-Your-Emoji

simple-audio-slicer. Easy audio slicing solution for preparing a dataset for RVC or So-VITS-SVC

yandex-tts-free. Free use of YandexSpeachKit in Russian language

ClothSwapTgBot. Бот который умеет менять одежду у людей и аниме персонажей

SonicTTS-Wrapper. A Python wrapper for the Cartesia Sonic TTS API, enabling customizable text-to-speech generation with voice, speed, and emotion control.

portable-maker. This project will help you quickly create a portable version of your python project

canvas-zoom. zoom and pan functionality

comfyui-rutext-lora-tranform. Extra node for Russian text Lora

VoicePolyglot. Trying to get your voice in another language with intonation preservation. The project uses XTTS , Whisper

canvas-zoom-showcase. Demonstration of features in canvas-zoom

elevenlabs-unleashed. Provides unlimited ElevenLabs API calls.

ranobelib_to_epub. Проект позволяет конвертировать любое ранобе с сайта ranobelib.me в epub

hailuo-tts-api. Wrapper for Hailuo TTS

canvas-zoom-lite. a light version of canvas-zoom that contains only the functions you need

RealtimeTTS. Converts text to speech in realtime

md_to_docx_converter. Gradio Markdown to Docx Converter

iMSteam-RU. Adds pirated alternatives for steam's games, russian resources (Online-fix, Rutracker, Rutor, Nnm-club, Small-games)

ebook2audiobook. Generate audiobooks from e-books, voice cloning & 1107+ languages!

v-express-webui. Webui for v-express

painthua-flask. HTML

SDTelegramBot. Телеграм бот для генерации и настройки генерации Stable Diffusion от AUTOMATIC1111 через встроенный FastAPI.

suno-api-fastapi. Use API to call the music generation AI of suno.ai, and easily integrate it into agents like GPTs.

fairseq-windows-prebuild. Prebuild wheel for fairseq on Windows. No need to install Microsoft Builder Tools 2019+

instructor-openrouter. structured outputs for llms

pyarmor_pipeline. Shell

fastapi_template_generator. Python

stable-diffusion-webui-forge. Python

AFFiNE. There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable and ready to use.

elevenlabs-wrapper. Simple wrapper to use Elevenlabs

tg_bot_template. My TG bot template

runpod-worker-a1111. Python

docker-elk. The Elastic stack (ELK) powered by Docker and Compose.

split_audio_speakers. split the audio into all speakers

rope. Backup, I'm not the author

sd-webui-replacer. A tab for sd-webui for replacing objects in picture using detection prompt

stable-waifu-tg-public. Проект вдохновленный и скопированный с телеграмм бота @stablewaifu

React-Pizza. React project where you can order a pizza