by NVIDIAReleased 29 October 2026
This model is designed to listen to audio recordings and convert the spoken words into written text. It excels at the task of accurately transcribing spoken content from various sources. A key feature is its ability to handle speech in 40 different languages. This model is strictly for speech recognition and cannot perform other general language or visual tasks.
You pay for what each request uses. No subscription, no minimum.
One minute of audio, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Second of audio | 0,011 DA |
per second of audio sent
Two companies run this model. OpenDunes sends each request to one of them, picked by price and speed. If it fails, the next one takes it.
You pay the price of the provider that served your request. Prices read 15:19 · speed over the last 30 minutes · uptime over 3 days.
Swap the base URL and the key. Your OpenAI code runs unchanged.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://opendunes.com/v1",
api_key=os.environ["OPENDUNES_API_KEY"],
)
with open("meeting.mp3", "rb") as f:
resp = client.audio.transcriptions.create(model="nvidia/nemotron-3.5-transcribe", file=f)
print(resp.text)Runs this request once on your balance.
About 0,67 DA per minute of audio. ↑ 0,011 DA per second of audio.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
This model is designed to listen to audio recordings and convert the spoken words into written text. It excels at the task of accurately transcribing spoken content from various sources. A key feature is its ability to handle speech in 40 different languages. This model is strictly for speech recognition and cannot perform other general language or visual tasks.
Deposit dinars with your Edahabia or CIB card. Every model, Nemotron 3.5 Transcribe included, is paid from that balance. No foreign card, no conversion.
NVIDIA names no languages for Nemotron 3.5 Transcribe. Arabic, French and Darja: not stated.
Speaker labels: not stated. Word timings: not stated.
Up to 25 MB as an upload. Longer audio goes in the request body.
NVIDIA. Released 29 October 2026.
Nemotron 3.5 ASR Streaming Multilingual 0.6B takes audio and writes out what is said, built to respond quickly in over 40 languages. It suits live work such as real-time captions and voice assistants, or pipelines that transcribe several languages, where text should appear while the speaker is still talking.
NVIDIA's 600M multilingual speech recogniser trained on over 670,000 hours, detecting every official EU language by itself and returning punctuated text with segment timestamps at a 6.34% average word error rate
Nemotron 3.5 Super VL reads text, pictures, documents, screenshots of app screens and video, and writes text back, taking in about a thousand pages at once. It is made for assistants that look at a screen or a document, then think and use the tools you connect. It thinks unless you switch that off, and you can limit how much effort it spends thinking. Nemotron 3 Super is the text-only model of the same size.
Nemotron 3 Ultra reads text and writes text back, thinks before it answers and can use the tools you connect. It is the biggest member of its family, meant for long-running assistant work such as coordinating other assistants, running coding assistants and deep research, where planning over many steps matters.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
40 languages
Read in the maker's description.
Transcribe spoken audio files into written text
40 languages
Convert recordings into a written transcription
40 languages
Process audio input to generate a written output
40 languages