Vladimir J

parakeet-tdt-0.6b-v3-fastapi-openai. A FastAPI wrapper for NVIDIA's new parakeet 0.6b v3 TTS 600m model designed for high-quality multilingual speech recognition, beating Whisper Large v3 and Whisper Large v3 turbo with blazing fast speeds on CPU.

opencode-local-setup. OpenCode local AI provider setup with automatic model syncing for LM Studio, vLLM, Ollama and any OpenAI-compatible API

Auralis-Enhanced. 🌌 Auralis - Transform text into natural speech at warp speed. High-performance TTS engine with voice cloning, streaming, and OpenAI-compatible API. Process entire novels in minutes!

linuxdeploy2025. [UPDATED 2025 ] Install and run GNU/Linux on Android proot (With updated ubuntu versions )

cozyvoice-fastapi. Python

mcp-llm-router. Python

DeepOpenAI. Unleash Next-Level AI! 🚀 💻 Code Generation: DeepSeek r1 + Claude 3.7 Sonnet - Unparalleled Performance! 📝 Content Creation: DeepSeek r1 + Gemini 2.0 - Superior Quality! 🔌 OpenAI-Compatible. 🌊 Streaming & Non-Streaming Support. ✨ Experience the Future of AI – Today! Click to Try Now! ✨

LocalAIVoiceChat. Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.

mcp-as-a-judge. MCP as a Judge is a behavioral MCP that strengthens AI coding assistants by requiring explicit LLM evaluations

amorfo. Whisper STT + Orpheus TTS + LLM using LM Studio to create a virtual assistant.

autotune-ai. ai autotune made real

Qwen3-TTS-Finetuning-Studio. Python

soprano-tts-enhanced. Enhanced Soprano TTS with OpenAI-compatible server and extensive text preprocessing

openpilot. openpilots

BCR-AI. A Basic Call Recorder for rooted Android devices

leelo. An awesome browser extension that reads aloud webpage content with one click

whisper-flash-v3-int8. Jupyter Notebook

chatterbox-tts-api. Local, OpenAI-compatible text-to-speech (TTS) API using Chatterbox, enabling users to generate voice cloned speech anywhere the OpenAI API is used (e.g. Open WebUI, AnythingLLM, etc.)

OpenGdrive. Google drive open source alternative, self hosted, free.

Handy. A free, open source, and extensible speech-to-text application that works completely offline.

large-v3-int8-faster-whisper. Faster Whisper Large V3 Int8 transcription with CTranslate2

page-assist. Use your locally running AI models to assist you in your web browsing

Snipaster. Python

unsloth-3090-multiple. unsloth-3090-multiple

o-llamarada. A modern and easy-to-use client for Ollama multiplatform Ios Android Windows and more..

ttsplugin. TTS implementation for the OpenAI api format. It can probably be used for any OpenAI api compliant service but its made for remsky/Kokoro-FastAPI.

KokoroTtsTexGernerationWebui. An extension to use Kokoro TTS in text generation webui

hp-fan-control. Thermal management and fan control solution for HP 14s-dq2079tu laptop running Linux

Open-SWE-agent. SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

synthetic-data-kit. Tool for generating high quality Synthetic datasets

kokoro-tts-addon. Local neural TTS for Browsers: fast, expressive, and offline—runs on modest hardware.

mobile-use. AI agents can now use real Android and iOS apps, just like a human.

WhisperLiveKit. Real-time & local speech-to-text, translation, and speaker diarization. With server & web UI.

fireworks. Fireworks AI Project from alphasec augmented with all models from fireworks ai

Linly-Talking. Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction method. 🤝🤖 It integrates various technologies like Whisper, Linly, Microsoft Speech Services, and SadTalker talking head generation system. 🌟🔬

Whisper-Fast-Cpu-OpenVino. Fast CPU-based Whisper transcription server using OpenVINO INT8 optimization. Real-time streaming, file upload with precision trimming, 100+ languages. Credits: OpenAI (Whisper) & Intel (OpenVINO)

VibeVoice-FastAPI. Standalone VibeVoice TTS with Gradio UI and FastAPI - Unlimited length audio generation with voice cloning

insanely-fast-whisper-web. Insanely Fast Whisper with Gradio Web UI and FastAPI - GPU accelerated speech-to-text

mcp-eyes-8k. eyes for blind llm agents , the neuralink for ai agents

kani-tts-arg. Python

ai-duet-fastapi. HTML

mcp-4k-eyes. An MCP Server that give Eyes to blind LLM agents.

ChatMode. Python

deepseek-ocr2-lazy. Efficient Lazy-Loading Server for DeepSeek-OCR-2 with MCP Support & Docker