Model reference · open weights
audio.cpp is an open-weight audio or speech model from CaptainArni, 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.
About
audio.cpp GGUF GGUF conversions of music and speech models for audio.cpp, the ggml-based native audio inference framework. ACE-Step 1.5 XL (bf16) The XL DiT is the larger ACE-Step 1.5 transformer: 32 layers of 2560 against turbo's 24 of 2048, with 32 attention heads of 128. Each file is self-contained the way audio.cpp's other ACE-Step GGUFs are — XL DiT, planner LM, text encoder and VAE in one file — so neither needs another download. XL Turbo is guidance-distilled and ignores guidancescale; XL SFT takes the CFG path. Both were converted from the float32 upstream snapshots with audiocppgguf --type bf16. Install Run The DiT variant is a load option, so name it explicitly: Measured on an RTX 5090 (CUDA), 20 s of audio in 15 s including model load, either variant. XL support landed in audio.cpp via PR #235; see docs/models/acestep.md there for the full option reference and for rebuilding this file yourself. Weights are MIT-licensed by ACE-Step; this repository only redistributes them in a different container format.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | CaptainArni |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Based on | ACE-Step/acestep-v15-xl-turbo, ACE-Step/acestep-v15-xl-sft |
| Released | 2026-08-16 |
| Popularity | 14k downloads / month |
| Licence | Open weights |
How it works
Variants
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.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| audio.cpp-gguf | — | GGUF | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys captainarni-audio-cpp for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (captainarni-audio-cpp 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="captainarni-audio-cpp" -F file=@audio.mp3
Details
Tags
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗