NurgaVoice

AI Transcription & Summarization Service

Open Source
Built with open-source models and fully open source
Self-Hosting
Deploy on your own infrastructure
Privacy First
No file storage, no logs - like your favorite VPN provider
No Registration
Simple and straightforward - just upload and process
Current Models
Speech Recognition
Whisper Model: Loading...
Used for audio transcription
Text Summarization
LLM Model: Loading...
Model information not available
Upload File
Supported formats: MP3, WAV, MP4, AVI, M4A, FLAC, OGG
Max size: 512MB
Toggle to enable/disable AI-powered text summarization
Identify and separate different speakers in the audio
Processing Status

Upload an audio or video file to get started