Nemotron 3.5 Transcribe

Transcriptions

nemotron-3.5-transcribe

Nvidia|Created Oct 30, 2026

Transcriptions

Nemotron 3.5 Transcribe is an open-weight, offline speech and audio model for transcription in 40 languages, with support for recordings up to one hour and a 65,536-token context. Its hybrid mixture-of-experts architecture activates approximately 4.3B parameters, including the audio encoder, and it is released in BF16, FP8, and NVFP4 precision.

Overview Specifications Activity Performance Uptime Examples API Reference

Compare

Endpoints and request shape

This page collects the public integration surface for the model: supported endpoints, available request parameters, and example calls through the NagaAI API.

Transcriptions

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-transcribe",
        file=f,
        prompt=None,
        language=None,
    )
print(transcription.text)

Supported Parameters

Available parameters for API requests

Language