Nemotron 3.5 ASR Streaming Multilingual 0.6B

Transcriptions

nemotron-3.5-asr-streaming-multilingual-0.6b

Nvidia|Created Oct 11, 2026

Transcriptions

Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice agents, and multilingual transcription pipelines.

Overview Specifications Activity Performance Uptime Examples API Reference

Compare

Pricing-50%

Pay-as-you-go rates for this model. More details in the billing guide.

Transcription (1 minute)

$0.0001

Capabilities

Code Example

Example code for using this model through our API with Python (OpenAI SDK) or cURL. Replace placeholders with your API key and model ID.

Basic request example. Ensure API key permissions. For more details, see our documentation.

from openai import OpenAI

client = OpenAI(base_url="https://api.naga.ac/v1", api_key="YOUR_API_KEY")

with open("audio.mp3", "rb") as f:
    transcription = client.audio.transcriptions.create(
        model="nemotron-3.5-asr-streaming-multilingual-0.6b",
        file=f,
        prompt=None,
        language=None,
    )
print(transcription.text)

Nemotron 3.5 ASR Streaming Multilingual 0.6B API Provider | NagaAI

Nemotron 3.5 ASR Streaming Multilingual 0.6B

Transcription (1 minute)

Nemotron 3.5 ASR Streaming Multilingual 0.6B

Transcription (1 minute)

Input Modalities

Output Modalities