Voice-to-text with push-to-talk for Wayland compositors
Transcribe and translate voice into LRC file using Whisper and LLMs (GPT, Claude, et,al). 使用whisper和LLM(GPT，Claude等)来转录、翻译你的音频为字幕文件。
On-device speech-to-text engine powered by deep learning
A dynamic, scalable AI chatbot built with Django REST framework, supporting custom training from PDFs, documents, websites, and YouTube videos. Leveraging OpenAI's GPT-3.5, Pinecone, FAISS, and Celery for seamless integration and performance.
Open-source voice dictation for Windows and Linux. Hold a hotkey, talk, and the transcript shows up at your cursor. Runs offline with Whisper.
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.
📱 🏃 🍎 Fitness application that’s used to keep track of your physical fitness data, daily calorie count, invite friends to work out together and ultimately get healthy.
Voice to text, one key to input.
Live bilingual subtitles for any app on macOS. Captures audio, transcribes speech, and translates — all from your menu bar.
Privacy-First Voice-to-Text with AI Enhancement for macOS
A bash script using OpenAI Whisper API for continuous audio transcription with automatic silence detection
Chrome Web Speech API
Voice-to-text CLI for terminal users
🎬 KaKa Subtitle Assistant | VideoCaptioner - English Branch - An intelligent subtitle assistant based on LLM and Faster Whisper, one click video and subtitle high speed muxing. No need for discreet GPU. Video sub generating, sentence breaking, proofing...all-in-one. Make subtitles with ease.
GUI for Faster‑Whisper‑XXL transcription tool: download YouTube audio, transcribe local files, manage models, and export multiple formats with themes and auto yt‑dlp updates.
Chrome extension for voice-to-text conversations with ChatGPT using OpenAI Whisper API
Codo-File is a code editor that primarily supports JavaScript and Python, with partial Dart support. Additionally, it features a real-time website editor where you can create your own website in the browser using HTML, CSS, and JavaScript. The project also includes an image-to-text feature and a voice-to-text feature .
This package can be used to connect Telegram bot to AI engines such as OpenAI ChatGPT, Dall-E, Midjourney, Stable Diffusion, etc.
AriaType is your private, local voice keyboard.
Free, local voice-to-text for Windows & macOS. No cloud, no account, no subscription.
Add a description, image, and links to the voice-to-text topic page so that developers can more easily learn about it.
To associate your repository with the voice-to-text topic, visit your repo's landing page and select "manage topics."