real-time-transcription 开源项目推荐（101 个）

royshil /obs-localvocal

OBS plugin for local speech recognition and captioning using AI

SamirPaulb /real-time-voice-translator

A desktop application that uses AI to translate voice between languages in real time, while preserving the speaker's tone and emotion.

nexmoe /DayBee

Desktop microphone recorder with real-time, on-device transcription, automatic audio segmentation, voice activity detection, and an MCP server for searching saved transcripts.

wenxuanzhang1209-cyber /meetdo

MeetDo——由筑听 · JKinco Listen 打造的开源“会议到行动”AI。支持自托管实时会议、本地 ASR/LLM、结构化会议纪要、DOCX/PDF。

royshil /obs-cleanstream

CleanStream is an OBS plugin that uses AI to clean live audio streams from unwanted words and utterances

shubhamshnd /Open-Cluely

Open-source free alternative to Cluely & Parakeet AI — real-time AI interview copilot with live transcription, screen capture, and AI-powered answers. Plug and play desktop app for coding interviews, technical interviews, and meetings. No subscription needed.

rryam /AuralKit

Swift package for real-time speech-to-text transcription with Apple SpeechAnalyzer and SpeechTranscriber on iOS 26 and macOS 26.

gladiaio /gladia-samples

Code samples for the Gladia speech-to-text API: pre-recorded and real-time transcription, audio intelligence, and voice agent integrations (LiveKit, Pipecat, Twilio, Discord, Google Meet) in Python, TypeScript and JavaScript.

deepgram-starters /flask-live-transcription

Get started using Deepgram's Live Transcription with this Flask demo app

deepgram-starters /node-live-transcription

Get started using Deepgram's Live Transcription with this Node demo app

royisme /pikabaka

Open-source AI interview copilot & meeting assistant. Real-time transcription, AI-suggested answers, screenshot reasoning. BYO API key, or run fully offline with Ollama. macOS + Windows.

Longt-audio /voxminutes

VoxMinutes — free, local-first meeting assistant for Windows. Records system audio + mic together with live transcription, 13-language translation, speaker diarisation with one-click renaming, desktop subtitles & AI meeting notes. Runs fully offline on local models; optional cloud models are pay-as-you-go. AGPL-3.0.

CloverIris /GraphMeeting

图会议 非线性会议软件 是一个颠覆传统会议方式的协作范式，GraphMeeting 把“所有人一起开麦”变成“每人一间单人录音棚”，系统再把所有声音实时拼成一张共享思维地图。专注于通过非线性结构展现和扩充每个人的想法。它不仅仅是一个会议工具，更是一个促进讨论和协作的环境，让参与者能够自由地表达自己的观点，同时通过智能技术帮助每个想法找到可能性、可行性，并最终形成可以实践的行动路径。每个参与者的声音都会被精准捕捉，AI将自动整理讨论内容，形成一个动态、不断扩展的思维结构图，帮助团队理清复杂问题，达成共识，并推进决策和行动。

Thairu-dev /StealthIt

一款隐秘、不绑定特定 AI 的桌面工具，使用 Python（PySide/Qt）构建。具备屏幕共享隐身、实时转录以及对多 LLM 的支持（Gemini、Ollama）。

Jemtaly /Whispering

A real-time transcription and translation tool implemented in Python based on the fast-whisper library.

colakang /echoai_helper

实时对话助手，支持双重音频转录和GPT响应，非常适合会议和面试。

NxtGenLegend /TreeHacks-ZoneOut

#3 Winner of Best Use of Zoom API at Stanford TreeHacks 2025! An AI-powered meeting assistant that captures video, audio and textual context from Zoom calls using multimodal RAG.

hi2brain /second-brain

A free, invisible AI interview copilot. Powered by Groq, Llama-3, and Whisper to provide real-time, context-aware answers during your job interviews. 🧠💼

BABIN-JOE /FLUENT-EDGE

Fluent Edge is an intelligent, real-time web application designed to help users improve their spoken English by analyzing live speech for transcription accuracy, grammar errors, and fluency quality. It combines speech recognition, punctuation restoration, grammar checking, and accuracy scoring in a seamless and interactive interface.

savander /real-time-captions

Real-time system audio captions and translation into English. Built using faster-whisper, PyQt6, and Torch.