Nemotron-Labs-Audex is an interactive Hugging Face Space for uploading audio and generating transcriptions, translations, descriptions, or answers to audio questions. It also converts typed text into spoken audio for users exploring speech and multimodal AI capabilities.
In the Other voice & speech space, Nemotron-Labs-Audex takes a focused approach. It focuses on processing and understanding audio, and converting text to speech, without building separate speech tools. Nemotron-Labs-Audex is a consumer product aimed at developers and users experimenting with speech AI. It is available for free. It ships for the web, and it can be self-hosted.
It is developed by NVIDIA. Among its 6 catalogued features are audio upload, transcription, and audio translation.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do