Speech / TTS
How to deploy turn-detector on a GPU cloud
A 135M-parameter speech model. Full specs, license and use cases.
turn-detector size and hardware requirements
135M
Total parameters
Dense (no MoE)
Architecture
F32
Published precision
0.6 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP32 | 0.5 GB | 0.6 GB | A16 | 1 | $0.059/hr |
| FP8 (quantized) | 0.1 GB | 0.2 GB | RTX 4070 Super | 1 | $0.110/hr |
| INT4 (quantized) | 0.1 GB | 0.1 GB | A16 | 1 | $0.059/hr |
How to run turn-detector
Run turn-detector with Transformers (Python)
Generic example using Hugging Face's transformers library, not from the model's own docs.
from transformers import pipeline
clf = pipeline("text-classification", model="livekit/turn-detector", device="cuda")
print(clf("example input"))Deploy turn-detector on Aquanode
Aquanode has no one-click deploy template for turn-detector; 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× A16 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