Speech / TTS
How to deploy parakeet-tdt-0.6b-v3 on a GPU cloud
A 627M-parameter speech model. Full specs, license and use cases.
parakeet-tdt-0.6b-v3 size and hardware requirements
627M
Total parameters
Dense (no MoE)
Architecture
F32
Published precision
2.8 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP32 | 2.3 GB | 2.8 GB | V100 | 1 | $0.060/hr |
| FP8 (quantized) | 0.6 GB | 0.7 GB | RTX 4070 Super | 1 | $0.110/hr |
| INT4 (quantized) | 0.3 GB | 0.4 GB | A16 | 1 | $0.059/hr |
How to run parakeet-tdt-0.6b-v3
Run parakeet-tdt-0.6b-v3 with Transformers (Python)
Generic example using Hugging Face's transformers library, not from the model's own docs.
from transformers import pipeline
asr = pipeline("automatic-speech-recognition", model="nvidia/parakeet-tdt-0.6b-v3", device="cuda")
result = asr("audio.wav")
print(result["text"])Deploy parakeet-tdt-0.6b-v3 on Aquanode
Aquanode has no one-click deploy template for parakeet-tdt-0.6b-v3; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (1× V100 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU pod