deepily/genie-in-the-box
Genie in the Box: Distill Whisper STT => Mistral-7B => Phind/Phind-CodeLlama-34B-v2 => GPT 3.5 => Coqui's TTS/OpenAI TTS
This project helps you interact with your computer using your voice for various tasks, from browsing the web to editing documents and even coding. You speak into a microphone, and the computer understands your commands and responds, either by performing actions or speaking back to you. This is for professionals who want to speed up their workflow and reduce manual input, such as writers, developers, or anyone who spends a lot of time on their computer.
No commits in the last 6 months.
Use this if you want to control your computer, browse the web, edit documents, or interact with development environments purely through voice commands, aiming for faster and more natural interaction.
Not ideal if you need a fully polished, ready-to-use voice assistant solution right now, as this is an active work-in-progress and still in development.
Stars
16
Forks
4
Language
Jupyter Notebook
License
AGPL-3.0
Category
Last pushed
Apr 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/deepily/genie-in-the-box"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
meizhong986/WhisperJAV
ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV
itsmevictor/clean-transcribe
A simple CLI to transcribe Youtube videos or local audio/video files and produce LLM-cleaned...
vivekuppal/transcribe
Transcribe is a real time transcription, conversation, Language learning platform. It provides...
BryceWG/BiBi-Keyboard
说点啥（BiBi Keyboard）:一个基于 Kotlin 的 Android 平台的 LLM 与 ASR 语音输入法键盘应用 An LLM ASR voice input method...
sindresorhus/awesome-whisper
🔊 Awesome list for Whisper — an open-source AI-powered speech recognition system developed by OpenAI