Oplatai website

SaaS Backend for front-end ASR

The app provides a user-friendly interface for interacting with a system that would eventually support Automatic Speech Recognition (ASR) for dysarthric speech and Text-to-Speech (TTS) functionality

This library allows you to easily use the Virlow Speech-to-Text API in your Node.js application.

Voice Enabled Sport Interval Timer using Transformers models

AI VM System - Log Search Frontend

SaaS ASR

Record audio data for ASR

Static build of whisper.cpp by ggerganov

A Chrome extension that enables voice-to-text input directly in your browser, with optional Groq LLM-powered text enhancement.

语音日记-小程序端

[NVIDIA ONLY] A minimal Gradio interface for Automatic Speech Recognition. Transcribe Audio in Malayalam language. (Requirements 6GB VRAM / 16GB RAM)

This is frontend of ASR Web Portal.

This repository provides a real-time speech-to-text transcription service using Vosk ASR (Automatic Speech Recognition) integrated with the Agent Voice Response system.

This repository provides a real-time speech-to-text transcription service using Google Cloud Speech-to-Text API integrated with the Agent Voice Response system.

Interactive web-based visualization tool for fortran AST, ASR using LFortran

This repository provides a real-time speech-to-text transcription service using Deepgram Speech-to-Text API integrated with the Agent Voice Response system.

A websocket proxy to use deepgram ASR. This allows to not share the API key and also control user usage.

Text and speech AI playground. The first version was vibe-coded with OpenAI Codex in the browser in ~10 days of 2 h/day sessions.