NVIDIA Parakeet
STT.ai does not run this model. This page is reference information about it.
Transcribe with the models we do run →
3.0%
WER
1
Languages
55.0x
Speed
CC-BY-4.0
License
About NVIDIA Parakeet
NVIDIA Parakeet TDT 1.1B is a state-of-the-art English ASR model using FastConformer architecture with Token-and-Duration Transducer (TDT). It achieves near-human accuracy on standard English benchmarks and is highly optimized for NVIDIA GPUs.
Languages Supported by NVIDIA Parakeet
Model Info
- ProviderNVIDIA
- Architecture-
- LicenseCC-BY-4.0
- UpdatedMar 2026
Frequently Asked Questions
NVIDIA Parakeet is a speech-to-text model by NVIDIA. STT.ai does not currently run NVIDIA Parakeet — this page is reference information about the model. For transcription on STT.ai, the model picker offers the Whisper family (Turbo, Large V3, Medium, Small).
On standard benchmarks, NVIDIA Parakeet achieves around 3.0% Word Error Rate. Real-world accuracy depends on audio quality, accent, and language; for noisy or accented recordings, expect a few percentage points higher WER.
NVIDIA Parakeet is not available on STT.ai. Its own licence terms govern running it yourself. STT.ai's free tier covers the Whisper models we do run — 600 minutes to start, then a monthly free top-up.
NVIDIA Parakeet is released under CC-BY-4.0, a permissive open-source license. You can self-host NVIDIA Parakeet on your own hardware or use our hosted version — both are commercially usable.
NVIDIA Parakeet supports 1 languages. Auto-detection picks the right language for most audio; you can also specify it manually for a small accuracy lift.
NVIDIA Parakeet processes audio at about 55.0x real-time on our GPUs. A 1-hour audio file finishes in under 1 minutes; longer files queue and notify by email when done.
NVIDIA Parakeet has 1.1B parameters. Larger models tend to be more accurate but slower; STT.ai hosts NVIDIA Parakeet on GPU so the parameter count doesn't affect your client-side performance.
NVIDIA Parakeet accepts every format STT.ai supports — MP3, WAV, M4A, FLAC, OGG, MP4, MKV, MOV, WebM, AVI, and others. Output as TXT, SRT, VTT, DOCX, JSON, or PDF.
Yes. Speaker diarization runs alongside NVIDIA Parakeet for every transcription — each speaker is labeled and you can rename them in the editor afterwards.
Yes. NVIDIA Parakeet runs in our managed environment — audio is processed and deleted by default and never used for training without explicit opt-in. Pro plans add client-side encryption for transcripts at rest.
Use the compare-stt tool to run NVIDIA Parakeet against any other supported model on the same audio — you'll see WER, segment count, speaker labels, and confidence scores side-by-side. The NVIDIA Parakeet vs Whisper Large V3 comparison is the most commonly run.
Yes. Specify "nvidia-parakeet" as the model parameter on the /v1/transcribe endpoint. Python and Node.js SDKs include NVIDIA Parakeet examples. Free API tier includes 100 minutes/month.
Yes. Because NVIDIA Parakeet is CC-BY-4.0-licensed, you can self-host it. STT.ai's open-source page lists the project repo and weights. Most production teams use our hosted version to skip GPU procurement, model swaps, and ops.