Marketplace · Speech-to-text

istupakov/parakeet-tdt-0.6b-v3-onnx

Call istupakov/parakeet-tdt-0.6b-v3-onnx through one OpenAI-compatible API. It's served by 1 host on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.

From
£0.03
per hour of audio
£1 buys about 33 hours of audio
Hosts
1
Loaded now
1

At a glance.

multilingual

  • Type: Speech-to-text
  • Hosts serving it now: 1 (1 with it loaded in memory)
  • Engines: vllm
  • Rentable: a whole host from £0.60 an hour (rentals)
python · openai sdk
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
                api_key=INPHERIO_API_KEY)
text = client.audio.transcriptions.create(
    model="istupakov/parakeet-tdt-0.6b-v3-onnx",
    file=open("audio.mp3", "rb"),
)

istupakov/parakeet-tdt-0.6b-v3-onnx in detail.

NVIDIA Parakeet TDT 0.6B V3 (Multilingual) [model](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) converted to ONNX format for [onnx-asr](https://github.com/istupakov/onnx-asr).

Published by
istupakov
Parameters
600M
Download size
652 MB (weights on Hugging Face)
Architecture
nemo-conformer-tdt
Licence
CC BY 4.0
Based on
nvidia/parakeet-tdt-0.6b-v3
Task
automatic speech recognition
Languages
en, es, fr, de, bg, hr, cs, da, nl, et, fi, el
First published
16 Aug 2025
Last updated
17 Feb 2026
Downloads (30 days)
121,361 on Hugging Face
Likes
70

onnx nemo-conformer-tdt automatic-speech-recognition asr onnx-asr en es fr de bg hr cs da nl et fi

The model card

Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.

NVIDIA Parakeet TDT 0.6B V3 (Multilingual) model converted to ONNX format for onnx-asr.

Install onnx-asr

pip install onnx-asr[cpu,hub]

Load Parakeet TDT model and recognize wav file

import onnx_asr
model = onnx_asr.load_model("nemo-parakeet-tdt-0.6b-v3")
print(model.recognize("test.wav"))

Code for models export

import nemo.collections.asr as nemo_asr
from pathlib import Path

model = nemo_asr.models.ASRModel.from_pretrained("nvidia/parakeet-tdt-0.6b-v3")

onnx_dir = Path("nemo-onnx")
onnx_dir.mkdir(exist_ok=True)
model.export(str(Path(onnx_dir, "model.onnx")))

with Path(onnx_dir, "vocab.txt").open("wt") as f:
    for i, token in enumerate([*model.tokenizer.vocab, ""]):
        f.write(f"{token} {i}\n")

Sources: istupakov/parakeet-tdt-0.6b-v3-onnx on Hugging Face. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.

Who's serving it.

Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.

Hosts serving istupakov/parakeet-tdt-0.6b-v3-onnx right now
HostTierPriceMeasured speedHealthStateRent
GTX 1080 Ti (11G)L1£0.03 /h audio1.9× real time78loaded£0.60/h

Live data, refreshed on every visit. How billing works.

Room on the grid for your machine.

Right now one machine serves istupakov/parakeet-tdt-0.6b-v3-onnx. If it drops, so does every request for it — a second host is what turns it into failover, and the grid needs that more than another copy. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.

Hosts now
1
1 loaded in memory
Price to beat
£0.03
per hour of audio
Fastest measured
1.9× real time

Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load istupakov/parakeet-tdt-0.6b-v3-onnx, and the platform benchmarks it on your hardware before your first request.