Audience
Multilingual contact-center platform developers who need accurate, deployable speech recognition across many languages and regional variants
About NVIDIA Parakeet
NVIDIA Parakeet-RNNT-1.1B is a multilingual automatic speech recognition model built for quality transcription across voice applications. With 1.1 billion parameters and training on more than 90,000 hours of speech, it supports 25 languages and regional variants, including English, Spanish, French, German, Italian, Arabic, Japanese, Korean, Portuguese, Russian, Hindi, Dutch, Danish, Norwegian, Czech, Polish, Swedish, Thai, Turkish, and Hebrew. The model automatically detects the spoken language and uses a universal tokenizer created by training language-specific tokenizers and merging them into a shared vocabulary, enabling efficient cross-lingual learning and deployment. Parakeet-RNNT produces case-sensitive transcripts with upper and lowercase text, punctuation, spaces, and apostrophes, making the output suitable for production voice applications and downstream language understanding.
Other Popular Alternatives & Related Software
mT5
Multilingual T5 (mT5) is a massively multilingual pretrained text-to-text transformer model, trained following a similar recipe as T5. This repo can be used to reproduce the experiments in the mT5 paper.
mT5 is pretrained on the mC4 corpus, covering 101 languages:
Afrikaans, Albanian, Amharic, Arabic, Armenian, Azerbaijani, Basque, Belarusian, Bengali, Bulgarian, Burmese, Catalan, Cebuano, Chichewa, Chinese, Corsican, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hmong, Hungarian, Icelandic, Igbo, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Kurdish, Kyrgyz, Lao, Latin, Latvian, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Nepali, Norwegian, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Samoan, Scottish Gaelic, Serbian, Shona, Sindhi, and more.
Learn more
Mintza
Mintza teaches you to speak a new language by actually speaking it, in live voice conversations with a bilingual AI teacher. Pick the language you speak and the one you are learning, then talk: real-time voice with natural pacing, no transcripts and no waiting for the app to think. When you freeze or slip up, your teacher corrects you in the moment, and if you get stuck it helps you in the language you already know, then brings you back.
Fifteen languages in any pairing and direction: English, Spanish, Portuguese, French, Italian, German, Greek, Chinese, Russian, Turkish, Swedish, Arabic, Japanese, Korean, and Hebrew, with regional accents such as Argentine Spanish, Parisian French, or Brazilian Portuguese. Rehearse a job interview, order coffee, navigate a doctor visit, or just chat about your day.
Sign in with Apple or Google for 10 free minutes, then subscribe for monthly conversation minutes. Available on iPhone, iPad, and Android.
Learn more
MAI-Voice-2
MAI-Voice-2 is Microsoft AI’s most expressive and natural-sounding text-to-speech model to date, built for production voice experiences where fidelity, language coverage, speaker consistency, and emotional range directly shape the user experience. It is designed for assistants, customer support, audiobooks, accessibility experiences, games, podcasts, courses, simulations, and creator workflows where voice quality must sound natural, fluid, and trustworthy. It expands from English-only support to 15 languages while maintaining naturalness and expressiveness, with support for English, Italian, French, German, Hindi, Spanish, Portuguese, Korean, Chinese, Turkish, Russian, Thai, Dutch, Romanian, and Hungarian. MAI-Voice-2 offers granular emotion control through tags such as sad, whispered, and excited, along with role-based expressive speech for experiences like motivational trainers, sports commentators, or character voices.
Learn more
OpenAI Whisper
Whisper is an automatic speech recognition (ASR) system developed by OpenAI for converting spoken language into text. It is trained on 680,000 hours of multilingual and multitask audio data collected from the web. The model is designed to handle diverse accents, background noise, and technical language with high accuracy. Whisper supports transcription in multiple languages as well as translation into English. It uses an encoder-decoder Transformer architecture to process audio inputs and generate text outputs. The system can also perform tasks like language identification and timestamp generation. Overall, Whisper enables developers to build robust voice-enabled applications with ease.
Learn more
Integrations
Company Information
NVIDIA
Founded: 1993
United States
build.nvidia.com/nvidia/parakeet-1_1b-rnnt-multilingual-asr/modelcard
Videos and Screen Captures
Other Useful Business Software
$300 Free Credits for Your Google Cloud Projects
Launch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
Product Details
Platforms Supported
On-Premises
Training
Documentation
Support
Online