NVIDIA Parakeet TDT 0.6B V3 Realtime
Model Information
v3NVIDIA Parakeet TDT 0.6B V3 Realtime on Together AI is a 600-million-parameter multilingual speech-to-text model optimized for live transcription and high-throughput inference. It supports automatic language detection across 25 European languages, automatic punctuation and capitalization, and word-level timestamps.
Model ID
togetherai.nvidia-parakeet-tdt-0.6b-v3
Use this ID when making API calls to reference this model
Provider
togetherai
Model Type
ASR
Accuracy Tier
premium
Supported Languages
bghrcsdanlenetfifrdeelhuitlvltmtplptroskslessvruuk
Automatic Language Detection: Yes
Streaming Transcription Languages
bghrcsdanlenetfifrdeelhuitlvltmtplptroskslessvruuk
Performance & Cost
Cost
$0.21000/hour
$0.00006/second
Features
Supported capabilities and functionalities
Core Features
Punctuation
Diarization
Streaming
Speaker Labels
Word Timestamps
Confidence Scores
Custom Vocabulary
Profanity Filtering
Noise Reduction
Voice Activity Detection
Subtitle Formats
SRT Support
VTT Support
Technical Specifications
Input/output formats and technical details
Subtitle Format Support
No subtitle formats supported
Supported Audio Encodings
WAVFLAC
Supported Sample Rates
16000 Hz