NVIDIA ParakeetNVIDIA
|
||||||
Related Products
|
||||||
About
GPTScribe is an audio and video transcription tool built to convert speech into accurate, readable text in seconds. Users can paste a link or upload an audio or video file, and GPTScribe immediately processes the content into a transcript that can be searched, edited, scrolled, or downloaded directly in the browser. It is built on a multilingual speech model fine-tuned on noisy, real-world recordings, helping it stay accurate with overlapping voices, soft accents, background music, phone-interview hiss, coffee-shop hum, and other imperfect audio conditions. Punctuation, casing, and paragraph breaks are added automatically so the transcript reads like something a human would type instead of a wall of words. GPTScribe supports more than 100 spoken languages with automatic detection, including multilingual recordings where speakers switch languages mid-conversation.
|
About
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.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
Journalists and research teams that need fast multilingual transcription, searchable interviews, translated transcripts, and ready-to-use subtitle exports
|
Audience
Multilingual contact-center platform developers who need accurate, deployable speech recognition across many languages and regional variants
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
Free
Free Version
Free Trial
|
Pricing
No information available.
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationGPTScribe
United States
www.gptscribe.ai/
|
Company InformationNVIDIA
Founded: 1993
United States
build.nvidia.com/nvidia/parakeet-1_1b-rnnt-multilingual-asr/modelcard
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
|
|||||
|
|
||||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
Adobe Premiere Pro
CapCut
DaVinci Resolve
Discord
Facebook
Final Cut Pro
FluidVoice
Instagram
LinkedIn
Pinterest
|
Integrations
Adobe Premiere Pro
CapCut
DaVinci Resolve
Discord
Facebook
Final Cut Pro
FluidVoice
Instagram
LinkedIn
Pinterest
|
|||||
|
|
|