Parakeet Tdt 0.6B V3
NVIDIA's Parakeet Tdt 0.6B V 3 is a multilingual automatic speech recognition model designed for high-throughput speech-to-text transcription, exceling at transcribing audio in 25 European languages with automatic language detection and punctuation. It is notable for its ability to transcribe long audio, supporting audio up to 24 minutes long with full attention.
Input
Output
Context
0K
Max Output
-
Parameters
600M
Technical Specifications
Model TypeAudio
Context Window448 tokens
Max Output TokensNot available
Parameters600M
Release DateAug 4, 2025
Training CutoffNot available
Licensecc-by-4.0
Open SourceYes
Input Modalities
Audio
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Parakeet Tdt 0.6B V3
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.