This model requires you to accept the Apache 2.0 license terms before download.
Description
Orpheus 3B — Canopy Labs LLM-based text-to-speech model built on Llama 3 architecture, expressive natural speech generation. Apache 2.0.
Tags
At a glance
| Kind | text-to-speech model |
|---|---|
| Precision | float32 |
| Container size | 14.1 GiB |
| Weights inside | 14.1 GiB |
| Components | 3 |
| Licence | Apache 2.0 |
What is inside the container
A .nbx container packs every part of orpheus-3b-0.1-ft — 3 components with weights, graphs and runtime settings — so one file is all the runtime needs.
| Component | Blocks | Layers | Weights |
|---|---|---|---|
| model | 0 | 28 | 12.3 GiB |
| lm_head | 0 | — | 1.8 GiB |
| codec.decoder | 0 | — | 50.2 MiB |
Default settings
The values the container ships with. They apply when you do not pass your own.
- Sample rate (Hz)
- 24000
- Max length
- 1200
- Temperature
- 0.6
- Top-p
- 0.95
- Top-k
- 50
Memory needed
The weights of orpheus-3b-0.1-ft take 14.1 GiB in float32. That is the floor for the memory the runtime has to place, spread over the devices it finds; activations come on top and grow with the size and length you ask for. A measured peak per device class is not published for this model yet.
Verify what you downloaded
Every download carries its SHA-256, and the file endpoint sends it in the X-NBX-SHA256 header. The container is 14.1 GiB (15,187,854,109 bytes).
$ sha256sum orpheus-3b-0.1-ft.nbx
246daf61e62a8b958b3061b605ea7fb5024e97b6659cf11af15cb91ec2d9610a
Questions
What is orpheus-3b-0.1-ft?
A text-to-speech model by canopylabs, distributed as a float32 .nbx container and licensed Apache 2.0.
How big is the download?
14.1 GiB, of which 14.1 GiB are weights.
How do I run it?
Install the runtime from the download page, then use the commands under “CLI Usage” below: neurobrix import canopylabs/orpheus-3b-0.1-ft, then neurobrix serve --model orpheus-3b-0.1-ft.
CLI Usage
$ neurobrix import canopylabs/orpheus-3b-0.1-ft
$ neurobrix serve --model orpheus-3b-0.1-ft
$ neurobrix run --prompt "your prompt here"
$ neurobrix stop