Model reference · open weights

orpheus-0.1-ft

orpheus-0.1-ft is an open-weight audio or speech model from canopylabs, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Audio canopylabs 1 variants 237k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

Specifications

What it is

Makercanopylabs
TypeAudio & music
Parameters (lead)3.8B
Variants1
Runs withtransformers
Based onmeta-llama/Llama-3.2-3B-Instruct, canopylabs/orpheus-3b-0.1-pretrained
Released2025-03-17
Popularity237k downloads / month
Likes728
LicenceOpen weights

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
orpheus-3b-0.1-ft3.8BBF16~8.7 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys orpheus-0-1-ft for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (orpheus-0-1-ft below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="orpheus-0-1-ft" -F file=@audio.mp3

Details

Languages, data & research

Languages

en

Tags

transformers safetensors llama text-generation text-to-speech en text-generation-inference endpoints_compatible

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want orpheus-0.1-ft on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More audio & music

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms