speach-to-text 开源项目推荐（105 个）

pmbstyle /Alice

Alice is a voice-first desktop AI assistant application built with Vue.js, Vite, and Electron. Advanced memory system, function calling, MCP support, optional fully local use, and more.

gaborvecsei /whisper-live-transcription

Live-Transcription (STT) with Whisper PoC

Dreaminko /VRCS

VRCS 是面向 VRChat 的字幕、翻译、语言学习和 AI 工具。

Abhi5h3k /Phantom-AI-Interview

🚀 Phantom-AI-Interview – A fun experiment exploring how AI can silently assist in virtual interviews, coding challenges, and exams. Uses OCR, LLMs, and automation to extract text, generate responses, and operate without a visible UI. 🔥

Igorcbraz /Calculadora

📐 Calculadora simples e intuitiva com suporte a comandos de voz e temas personalizados 📏

sterlp /eclipse-peon-ai

AI harness for and with Eclipse IDE with the focus on offline LLM with llama.cpp. Build with LangChain4J. Supports Ollama, LM Studio, llama.cpp, unsloth or cloud providers like with OpenA API, Anthropic Claude, Google Gemini, Mistral, GitHub Copilot. Contributions are highly welcome!

bogdanr /fono

Press a key, speak, text lands at your cursor. Press another, get a spoken answer. Local-first, lightweight voice dictation and assistant for Linux. φ

JRufer /VoxCtrl

Use key or voice commands to direct your voice to any app or service you require, local or remote.

MoHamed-B-M /flambo

Flambo: Open-source Android Voice Recorder & Transcriber | Material 3 Expressive UI, Offline Speech-to-Text (Vosk), Noise Reduction & Live Waveforms

Avi-D-coder /whisper.nvim

local speech to text in Neovim

DanielTerletzkiy /chat-gtp-assistant

nodejs script that enables continuous conversation with voice recognition and tts speaker responses

dennisyang1986 /flash-transcribe

Flash Transcribe 是一个完全独立、免费开源的音频转文字工具。市面上许多语音转文字服务都需要付费订阅，而本项目旨在提供一个完全免费、功能强大的替代方案。

Mouez-Yazidi /WhisperMesh

WhisperMesh is an advanced chatbot that integrates voice and text interactions, delivering personalized responses through LLM models and a sophisticated vector database. Leveraging the RAG framework from Haystack, it ensures engaging, data-driven conversations that adapt to your preferred style.

dsaad68 /mispher

Mispher turns speech into clean text anywhere on macOS, then goes further - dictation cleanup, rewrite-in-place, translation, and an on-device agent that plans, uses tools, and answers. No cloud, no accounts. Nothing leaves your Mac.

spartanhaden /whisper-typer

A small script that types what you say using whisper while holding a hotkey

leopiney /wolfbud

Using Scribe v2 API from ElevenLabs so that I don't have to pay Monologue, WhisperFlow, or SuperWhisper. There's no existing association with or endorsement of this application from ElevenLabs.

davidgao7 /museum-tour-guide

Your personalized museum tour guide!

shiipou /openai_stt

OpenAI STT custom component for HA

sangtaik /STT

wav2vec를 사용한 STT 기능을 사용하여 음성인식 및 PPT 도우미 기능을 추가

mishrababhishek /chatbot

AI Chatbot answers students' queries about their college program using Natural Language Processing. It's built with Python's TensorFlow, FastAPI, Uvicorn, React, and Tailwind CSS. The frontend has a modern interface while the backend provides fast and efficient request handling. The chatbot can be customized for specific college requirements