Docs / Models

Model catalogue

Models for continuous inference.

Models available on .wave, and the API that serves each.

NVIDIA Public beta

Speech ↔ speech · full duplex

Nemotron VoiceChat 11B

nemotron-voicechat Live API

Listen and respond in the same live session, with audio plus user and assistant transcript events.

View model →

NVIDIA Public beta

Speech → text · streaming

Nemotron 3.5 ASR Streaming 0.6B

nemotron-asr-streaming Realtime API · Deepgram-compatible API

Stream live audio and receive punctuated text as people speak, in 32 languages or with automatic language detection.

View model →