最有价值项目

It's Python-based virtual assistant capable of performing various tasks using voice commands. It utilizes speech recognition, web scraping, automation, and external APIs to provide a wide range of functionalities.

This project is a conversational AI program that uses speech recognition, text-to-speech, and the OpenAI API to generate responses to user prompts, allowing for a natural conversation flow.

AI-powered medical terms detection tool.

Practice real voice interviews with an AI interviewer, get coding problems evaluated live, and receive a scored performance report.

Privacy-first voice-to-text for macOS and Windows. Local Whisper (Metal/CUDA) or Groq cloud, with LLM post-processing. Built with Rust + Tauri 2.

Python wrapper for OpenAI's Whisper for processing all audio files in a specified folder and creating raw text + transcript with time stamps

A speech-to-text bot for discord with music commands and more using NodeJS. Ideally for controlling your Discord server using voice commands, can also be useful for hearing-impaired people.

A self-hosted, keyboard-driven cockpit for running a whole fleet of Claude Code agents at once. Worktrees, command palette, scheduler, voice — every layer stacks, so you ship far more than hand-juggling terminals. Your machine, your keys, no telemetry.

Music advice from a conversational interface powered by Algolia

A Deepgram client for Dart and Flutter, supporting all Speech-to-Text and Text-to-Speech features on every platform.

Speech-to-Speech conversational AI using Azure OpenAI Service and Azure Speech Services

ONNX speech pipeline library for ASR, diarization, VAD, and denoising

Minimalist voice-to-text app. Hold hotkey, speak, auto-paste. Cloud transcription via OpenAI/Groq.

Vim Speech Recognition Experiments

Natural Language Processing Nanodegree from Udacity Platform, in which I implement Hidden Markov Model for POS Tagger, Bidirectional LSTM for English-French Machine Translation, and End-to-End LSTM-based Speech Recognition

Turn CAPSLOCK key into Dictation Key

Python SDKs for Speechmatics APIs

htop for your LLM inference cluster

Manalyzer: End-to-end Automated Meta-analysis with Multi-agent System

A lightweight post-training framework for LLMs and VLMs. 51 algorithms, 38 verified models. Scales with DeepSpeed, vLLM, and Ray.