NVIDIA logo

Nemotron 3.5 0.6B ASR Streaming Multilingual

Nemotron 3.5 0.6B ASR Streaming Multilingual is NVIDIA's speech to text model. A compact 0.6B-parameter FastConformer-RNNT streaming ASR model optimized for low-latency multilingual transcription across 40+ languages.
Specifications
Canonical IDnvidia-nemotron-3-5-0-6b-asr-streaming-multilingual
TypeSpeech to Text
StatusActive
CreatorNVIDIANVIDIA
Input ModalitiesAudio
Output ModalitiesText
Parameters0.6B

Capabilities

Input1/5
Text·
Image·
Audio
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Cheapest Instances to Run It

Cloud GPU instances that can host Nemotron 3.5 0.6B ASR Streaming Multilingual, ranked by cheapest on-demand price. The model needs about 1 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
g6f.largeAWSL43 GB$0.202/hrus-east-1
Standard_NV4as_v4AzureAMD Radeon Instinct MI2516 GB$0.233/hrwestus2
g6f.xlargeAWSL43 GB$0.237/hrus-east-1
7 more instances can run Nemotron 3.5 0.6B ASR Streaming Multilingual
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Nemotron 4 15BAvailable
Nemotron 3 Ultra 550B A55B1.0M$0.600$2.40Available
Nemotron 3.5 Content Safety128KAvailable
Nemotron Nano 3 30B A3B Omni Reasoning256KAvailable
Nemotron Super 3 120B256K$0.150$0.650Available
Nemotron Nano 3 30B262K$0.060$0.240Available
Nemotron 3.5 0.6B ASR Streaming MultilingualCurrent
Nemotron Nano 3 30B A3B OmniAvailable
Nemotron Nano 3 30B A3B ReasoningAvailable
Nemotron Nano 3 4BAvailable
Nemotron 3Available

Model IDs

nvidia-nemotron-3-5-0-6b-asr-streaming-multilingual
nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b