Nemotron 3.5 ASR Streaming 0.6B is an open-weight automatic speech recognition model for real-time audio transcription. Developers can run it locally with Python tooling or access hosted inference through Hugging Face providers and APIs.
In the Speech to text space, Nemotron 3.5 Asr Streaming 0.6b takes a focused approach. It focuses on building low-latency speech-to-text transcription for streaming audio. It is built as an open-source project for AI developers and speech technology researchers. The project is open source (Apache-2.0). It runs on the web, the command line, and API, and it can be self-hosted.
It is developed by NVIDIA, and it first shipped in 2026. The project is developed in the open on GitHub with 10 stars and 1 commit in the last 90 days. Among its 6 catalogued features are streaming transcription, automatic speech recognition, and multilingual recognition. It exposes integrations via a public API.
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