ai-transcription 开源项目推荐（59 个）

Hugo-Dz /on-device-transcription

A ready-to-use, minimal app that converts any speech into text.

madderscientist /noteDigger

在线前端频谱分析扒谱 front-end music transcription

jakovius /voxd

VOXD is a speech-to-text, voice-typing, dictation software for linux distributions. It is an open-source, free of charge, USER-FRIENDLY software, for as many linux distros as possible.

Stage-Whisper /Stage-Whisper

The main repo for Stage Whisper — a free, secure, and easy-to-use transcription app for journalists, powered by OpenAI's Whisper automatic speech recognition (ASR) machine learning models.

jetkai /openai-for-java

OpenAI/ChatGPT library for Java - Requires JDK 11 at minimum.

MudAccountant /ultra-edit

Ultra Edit 2026 pre-configured environment for seamless desktop software utility deployment on isolated local workstations.

madderscientist /timbreAMT

explore AMT from the perspective of timbre; 超轻量音乐分离转录

ItisShikhar /captioncat

Design and render expressive, animated captions for video and audio with reusable presets. Create, customize, and manage your own caption styles with Preset Studio.

Malith-Rukshan /whisper-transcriber-bot

🎙️ AI-powered Telegram bot for voice-to-text transcription using OpenAI Whisper. CPU-only, no GPU required, privacy-focused with local processing.

keatonkraiger /Whisper-Transcribe-and-Translate-Tutorial

This contains a practical guide for non-technical users on how to use OpenAI's Whisper for transcription and translation

LinuxDevil /ScreenRecAI-Desktop

Offline, privacy-first screen recorder with local AI transcription and smart summaries. Built with Electron, React, and TypeScript—capture desktop video, auto-generate transcripts, and get instant AI-powered meeting and lesson insights, all cross-platform and fully customizable.

nikhil-reddy05 /auto-captions

Automatically generate accurate, per-word video captions with timestamps using Whisper ASR and FFmpeg, perfect for YouTube, social media, and accessibility.

Baisampayan1324 /AI-MOM

Al MOM 是一个 AI 驱动的会议智能平台，使用 FastAPI、Whisper、Groq 和 OpenRouter 提供实时转写、说话人识别和多 LLM 摘要，以带来智能会议洞察。

honoredwhac /Whisper-Desktop---OpenAI-Whisper-Transcriber-2026

Whisper-Desktop - offline speech-to-text with 99% accuracy, 97 languages, and real-time transcription.

walidght /Trend-Lens

An AI-powered intelligence platform to reverse-engineer short-form virality. Identify high-performing outliers and extract winning content strategies across Instagram, TikTok, and YouTube.

SU-PER-NOVA /whisper-offline-video-audio-transcriber

"An offline video & audio transcription tool powered by OpenAI Whisper. Convert your tutorials, lectures, and podcasts into accurate text transcripts and use AI to generate summaries, notes, and mind maps — saving hours of time and boosting productivity."

EdwardTang /whisper-assistant-cursor

🚀📜 Customized For Agentic AI: Enhanced the Whisper Assistant extension with improved setup scripts and documentation, ensuring seamless integration and functionality on Linux platforms.

EvilIrving /ai-transcriber

Moved to https://github.com/EvilIrving/mediabrief — MediaBrief

clancymendonca /Flick

Flick is a powerful AI-driven SaaS platform for real-time video sharing and collaboration, crafted for both web and desktop environments. Designed for seamless video recording, streaming, and sharing without third-party dependencies, Flick offers teams and individuals an integrated workspace to create, manage, and share video content in real-time.

TN019 /scripto

Local, free batch transcription & subtitle translation for macOS/Windows — nothing leaves your machine.