arihanv/Shush
Shush is an app that deploys a WhisperV3 model with Flash Attention v2 on Modal and makes requests to it via a NextJS app
This project is a demonstration for developers who want to deploy high-performance AI models and reliable, auto-scaling APIs. It shows how to integrate a powerful audio transcription model, WhisperV3, as a backend service with a user-friendly Next.js frontend. Developers can learn how to build full-stack applications with AI inference.
220 stars. No commits in the last 6 months.
Use this if you are a developer looking for a practical example of deploying an advanced AI model like WhisperV3 with a scalable backend and a modern web frontend.
Not ideal if you are an end-user simply looking for a tool to transcribe audio without needing to understand or build the underlying application architecture.
Stars
220
Forks
38
Language
TypeScript
License
MIT
Category
Last pushed
Jun 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/arihanv/Shush"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SYSTRAN/faster-whisper
Faster Whisper transcription with CTranslate2
machinelearningZH/audio-transcription
Transcribe any audio or video file. Edit and view your transcripts in a standalone HTML editor.
saharmor/whisper-playground
Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/
shhossain/BanglaSpeech2Text
BanglaSpeech2Text: An open-source offline speech-to-text package for Bangla language. Fine-tuned...
oseiskar/autosubsync
Automatically synchronize subtitles with audio using machine learning