Nemotron 3.5 ASR Streaming Multilingual 0.6B · deepinfra

Nemotron 3.5 ASR Streaming Multilingual is an open 0.6B-parameter prompt-conditioned cache-aware FastConformer-RNNT model, engineered for low-latency streaming transcription across 40+ languages. It powers real-time captioning, voice agents, and multilingual transcription pipelines—replacing separate per-language Whisper deployments with a single inference pass.

Base modelAll models on this baseAll models of the providerto the provider

All NVIDIA models at every provider

Price, $ $0.0001998 / minute

Context —

Accepts —

Last checked 04.11.2026 12:00:14 UTC

Source —