从 65,707 个高星开源项目里，
找到你要的下一个。

auto-subs 是用 TypeScript 编写的 AI 工具，用于人工智能方向的建模与推理。

On-device subtitle generation that connects directly to DaVinci Resolve, Premiere, and After Effects.

openscreen 是用 TypeScript 编写的多媒体工具，用于处理音视频内容，主打开源免费。

Record your screen, ship a demo. Free and open-source, GPU-accelerated, no watermarks, no subscriptions. Windows, macOS, Linux. Actively maintained.

LiveCaptions-Translator 是用 C# 编写的多媒体工具，用于处理音视频内容，主打轻量、功能完整、实时。

Lightweight and powerful real-time audio/speech translation tool based on Windows LiveCaptions.

Hold a key, speak, release — AI-polished text appears at your cursor in any app. Open-source voice input for macOS & W…

Hold a key, speak, release — AI-polished text appears at your cursor in any app. Open-source voice input for macOS & Windows. (按住快捷键说话，松开即得润色后的文字)

whisper-asr-webservice 是用 Python 编写的 AI 工具，用于大模型与智能体应用开发。

OpenAI Whisper ASR Webservice API

whisper-standalone-win 是一个 AI 工具，用于大模型与智能体应用开发，主打速度快。

Whisper & Faster-Whisper standalone executables for those who don't want to bother with Python.

LLaMA-Omni 是用 Python 编写的 AI 工具，用于大模型训练与推理。

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabili…

willow 是用 C 编写的学习资料，用于系统学习与查阅，主打支持自托管、开源免费。

Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative

whishper 是用 Svelte 编写的前端库，用于构建 Web 页面与界面。

Transcribe any audio to text, translate and edit subtitles 100% locally with a web UI. Powered by whisper models!

STT 是用 C++ 编写的学习资料，用于系统学习与查阅，主打易用。

🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.

foundry-local 是用 C++ 编写的 AI 工具，用于大模型与智能体应用开发。

awesome-whisper 是一个资源清单，按主题汇总同类优质资源，主打开源免费。

🔊 Awesome list for Whisper — an open-source AI-powered speech recognition system developed by OpenAI

WhisperJAV 是用 Python 编写的 AI 工具，用于大模型与智能体应用开发。

ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV

开源免费的 Wispr Flow 替代方案 | 集成FunASR本地模型和可配置大语言模型的下一代中文桌面语音工作流

开源免费的 Wispr Flow 替代方案 | 集成FunASR本地模型和可配置大语言模型的下一代中文桌面语音工作流

tensorflow-speech-recognition 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks

vad 是用 TypeScript 编写的前端库，用于构建 Web 页面与界面，主打易用。

Voice activity detector (VAD) for the browser with a simple API

transcribe.cpp 是用 C++ 编写的 AI 工具，用于大模型训练与推理。

ggml speech-to-text inference for 16+ model families

audapolis 是用 TypeScript 编写的多媒体工具，用于处理音视频内容。

an editor for spoken-word audio with automatic transcription

typewhisper-mac 是用 Swift 编写的 AI 工具，用于大模型训练与推理。

Local speech-to-text for macOS on-device AI, fully private, optional cloud

kalliope 是用 Python 编写的自动化工具，用于流程自动化编排。

Kalliope is a framework that will help you to create your own personal assistant.

react-native-executorch 是用 TypeScript 编写的 AI 工具，用于大模型与智能体应用开发，主打高性能。

High-performance, privacy-first on-device AI inference library for React Native, powered by PyTorch's ExecuTorch runtime

dsnote 是用 C++ 编写的桌面应用，用于桌面端程序开发。

Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.

收集户晨风的所有内容

收集户晨风的所有内容

voxtype 是用 Rust 编写的开源项目，主题标签有限，建议打开仓库查看具体用途。

Voice-to-text with push-to-talk for Wayland compositors