NVIDIA Nemotron 3.5 ASR Streaming Multilingual 0.6B is a real-time speech recognition model built for fast, scalable multilingual transcription. Discover how its cache-aware FastConformer-RNNT architecture, 40 language-locales, configurable streaming latency, automatic language detection, native punctuation, and high-concurrency inference support modern voice agents, live transcription, contact centers, and conversational AI applications.
