NVIDIA Parakeet / Canary / Nemotron Speech
Fast NVIDIA speech recognition models, including streaming ones for real-time use. Parakeet TDT v3 and Nemotron 3.5 ASR understand Russian. The new Nemotron 3.5 Transcribe (34B, 4.3B active, OpenMDW 1.1) transcribes recordings of up to an hour in 40 languages, translates speech, splits it by speaker, puts word timestamps and answers questions about the content (questions in English only); all tasks are available for Russian. Ready files only, live streaming is not supported. The figures are the authors: 5.33% word errors on English in the open Hugging Face leaderboard.
- Developer
- NVIDIA, USA
- First release
- Dec 2023
- Latest release
- Oct 2026
- Sizes
- 110M – 34B-A4.3B
- License
- Commercial use with conditionsMixed: Parakeet and Canary mostly CC-BY-4.0 (the first Canary-1B is non-commercial), Parakeet Unified and Nemotron Speech Streaming under the NVIDIA Open Model License, Nemotron 3.5 ASR and Transcribe under OpenMDW
- Russian
- Supported
- Running
- On your own serverAlso runs without a GPU
- Industries
- Customer support, Media and production, Documents and accounting
What it does
- Transcribing calls and meetings
- Video subtitles
- Real-time voice input
- Tagging audio archives
Where it is used
Hardware requirements
Versions
- Nemotron 3.5 Transcribe 30B-A4B (40 языков, до часа)
- Nemotron 3.5 ASR Streaming 0.6B
- Parakeet Unified 0.6B
- Nemotron Speech Streaming 0.6B
- Parakeet TDT 0.6B v3 и Canary-1B v2
- Canary-Qwen-2.5B
- Parakeet TDT 0.6B v2
- Canary-1B
- Parakeet CTC 0.6B
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.
Frequently asked questions
Can NVIDIA Parakeet / Canary / Nemotron Speech be used in a commercial project?
With conditions. License: Mixed: Parakeet and Canary mostly CC-BY-4.0 (the first Canary-1B is non-commercial), Parakeet Unified and Nemotron Speech Streaming under the NVIDIA Open Model License, Nemotron 3.5 ASR and Transcribe under OpenMDW. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.
What hardware does NVIDIA Parakeet / Canary / Nemotron Speech need?
At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does NVIDIA Parakeet / Canary / Nemotron Speech support Russian?
Yes, Russian is listed on the model card.
Where can I download NVIDIA Parakeet / Canary / Nemotron Speech and what does it cost?
The NVIDIA Parakeet / Canary / Nemotron Speech weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.
How I deploy it for clients
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Comparisons
Similar models
Speech recognition in 99 languages, including Russian. The de facto standard for transcribing calls and meetings. Hugging Face's faster Distil-Whisper is English only.
DetailsSpeech to textGigaAMSber · RussiaCommercial use allowedSber's models for Russian speech recognition, among the most accurate for Russian. Includes emotion recognition, v3 with punctuation, and a multilingual version (Russian, Kazakh, Kyrgyz, Uzbek).
DetailsSpeech to textQwen3-ASRAlibaba (Qwen) · ChinaCommercial use allowedSpeech recognition models from the Qwen team for 50+ languages, including Russian. They handle noise, singing and accents well.
DetailsSource: huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.