Instructions to use audio-cpp/audio.cpp-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use audio-cpp/audio.cpp-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="audio-cpp/audio.cpp-gguf",
	filename="HTDemucs-GGUF/htdemucs-f16.gguf",
)

llm.create_chat_completion(
	messages = "\"The answer to the universe is 42\""
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use audio-cpp/audio.cpp-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf audio-cpp/audio.cpp-gguf:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf audio-cpp/audio.cpp-gguf:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf audio-cpp/audio.cpp-gguf:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf audio-cpp/audio.cpp-gguf:UD-Q4_K_XL

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf audio-cpp/audio.cpp-gguf:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf audio-cpp/audio.cpp-gguf:UD-Q4_K_XL

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf audio-cpp/audio.cpp-gguf:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf audio-cpp/audio.cpp-gguf:UD-Q4_K_XL

Use Docker

docker model run hf.co/audio-cpp/audio.cpp-gguf:UD-Q4_K_XL

LM Studio
Jan
Ollama
How to use audio-cpp/audio.cpp-gguf with Ollama:
```
ollama run hf.co/audio-cpp/audio.cpp-gguf:UD-Q4_K_XL
```

Unsloth Studio

How to use audio-cpp/audio.cpp-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for audio-cpp/audio.cpp-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for audio-cpp/audio.cpp-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for audio-cpp/audio.cpp-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use audio-cpp/audio.cpp-gguf with Docker Model Runner:
```
docker model run hf.co/audio-cpp/audio.cpp-gguf:UD-Q4_K_XL
```

Lemonade

How to use audio-cpp/audio.cpp-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull audio-cpp/audio.cpp-gguf:UD-Q4_K_XL

Run and chat with the model

lemonade run user.audio.cpp-gguf-UD-Q4_K_XL

List all available models

lemonade list

audio.cpp-gguf / README.md

audio-cpp

Add files using upload-large-folder tool

8cb1668 verified 2 days ago

preview code

Raw

History Blame Contribute Delete

5.35 kB

	---
	license: other
	library_name: audio.cpp
	pipeline_tag: text-to-speech
	tags:
	- gguf
	- audio.cpp
	- text-to-speech
	- automatic-speech-recognition
	- voice-conversion
	- speech
	---

	# audio.cpp GGUF Model Packages

	This directory contains audio.cpp-native GGUF conversions of multiple speech models. These files are intended for use with [audio.cpp](https://github.com/0xShug0/audio.cpp).

	For conversion details, supported layouts, direct-file loading, sidecar embedding, and the latest compatibility notes, see the audio.cpp GGUF guide:

	- https://github.com/0xShug0/audio.cpp/blob/main/docs/gguf.md

	!!! Automated audio checks are intentionally strict and may flag length, log-mel, or transcript drift that can still sound acceptable to human listeners. Validate the exact file, backend, and route you plan to use. These converted weights are provided as-is; use them at your own risk.


	## Files

	\| Directory \| Files \| audio.cpp family \| Original model license \|
	\|---\|---\|---\|---\|
	\| `HTDemucs-GGUF` \| `htdemucs-f16.gguf`, `htdemucs-q8_0.gguf` \| `htdemucs` \| See original model package \|
	\| `Higgs-Audio-v3-STT-GGUF` \| `higgs-audio-v3-stt-f16.gguf`, `higgs-audio-v3-stt-q8_0.gguf` \| `higgs_audio_stt` \| Apache-2.0 \|
	\| `IndexTTS2-GGUF` \| `index-tts2-orig.gguf`, `index-tts2-f16.gguf`, `index-tts2-q8_0.gguf` \| `index_tts2` \| bilibili Model Use License Agreement \|
	\| `Irodori-TTS-500M-v3-GGUF` \| `irodori-tts-500m-v3-f16.gguf`, `irodori-tts-500m-v3-q8_0.gguf` \| `irodori_tts` \| MIT \|
	\| `Irodori-TTS-600M-v3-VoiceDesign-GGUF` \| `irodori-tts-600m-v3-voicedesign-f16.gguf`, `irodori-tts-600m-v3-voicedesign-q8_0.gguf` \| `irodori_tts` \| MIT \|
	\| `MOSS-TTS-Local-v1.5-GGUF` \| `moss-tts-local-v1.5-bf16.gguf`, `moss-tts-local-v1.5-q8_0.gguf` \| `moss_tts_local` \| Apache-2.0 \|
	\| `MOSS-TTS-Nano-100M-GGUF` \| `moss-tts-nano-100m-bf16.gguf`, `moss-tts-nano-100m-q8_0.gguf` \| `moss_tts_nano` \| Apache-2.0 \|
	\| `Mel-Band-RoFormer-GGUF` \| `mel-band-roformer-f16.gguf`, `mel-band-roformer-q8_0.gguf` \| `mel_band_roformer` \| MIT \|
	\| `MioCodec-25Hz-44.1kHz-v2-GGUF` \| `miocodec-25hz-44khz-v2-orig.gguf`, `miocodec-25hz-44khz-v2-f16.gguf`, `miocodec-25hz-44khz-v2-q8_0.gguf` \| `miocodec` \| MIT \|
	\| `MioTTS-1.7B-GGUF` \| `miotts-1.7b-orig.gguf`, `miotts-1.7b-bf16.gguf`, `miotts-1.7b-q8_0.gguf` \| `miotts` \| Apache-2.0 \|
	\| `Nemotron-3.5-ASR-Streaming-0.6B-GGUF` \| `nemotron-3.5-asr-streaming-0.6b-f16.gguf`, `nemotron-3.5-asr-streaming-0.6b-q8_0.gguf` \| `nemotron_asr` \| OpenMDW-1.1 \|
	\| `OmniVoice-GGUF` \| `omnivoice-f16.gguf`, `omnivoice-q8_0.gguf` \| `omnivoice` \| Apache-2.0 \|
	\| `Qwen3-ASR-0.6B-GGUF` \| `qwen3-asr-0.6b-f16.gguf`, `qwen3-asr-0.6b-q8_0.gguf` \| `qwen3_asr` \| Apache-2.0 \|
	\| `Qwen3-ASR-1.7B-GGUF` \| `qwen3-asr-1.7b-f16.gguf`, `qwen3-asr-1.7b-q8_0.gguf` \| `qwen3_asr` \| Apache-2.0 \|
	\| `Qwen3-ForcedAligner-0.6B-GGUF` \| `qwen3-forced-aligner-0.6b-f16.gguf`, `qwen3-forced-aligner-0.6b-q8_0.gguf` \| `qwen3_forced_aligner` \| Apache-2.0 \|
	\| `Qwen3-TTS-12Hz-1.7B-Base-GGUF` \| `qwen3-tts-12hz-1.7b-base-orig.gguf`, `qwen3-tts-12hz-1.7b-base-bf16.gguf`, `qwen3-tts-12hz-1.7b-base-q8_0.gguf` \| `qwen3_tts` \| Apache-2.0 \|
	\| `Qwen3-TTS-12Hz-1.7B-CustomVoice-GGUF` \| `qwen3-tts-12hz-1.7b-customvoice-bf16.gguf`, `qwen3-tts-12hz-1.7b-customvoice-q8_0.gguf` \| `qwen3_tts` \| Apache-2.0 \|
	\| `Qwen3-TTS-12Hz-1.7B-VoiceDesign-GGUF` \| `qwen3-tts-12hz-1.7b-voicedesign-bf16.gguf`, `qwen3-tts-12hz-1.7b-voicedesign-q8_0.gguf` \| `qwen3_tts` \| Apache-2.0 \|
	\| `SeedVC-MLX-GGUF` \| `seed-vc-mlx-orig.gguf`, `seed-vc-mlx-f16.gguf`, `seed-vc-mlx-q8_0.gguf` \| `seed_vc` \| GPL-3.0 \|
	\| `Stable-Audio-3-Medium-GGUF` \| `stable-audio-3-medium-f16.gguf`, `stable-audio-3-medium-q8_0.gguf` \| `stable_audio` \| Stability AI Community License \|
	\| `Stable-Audio-3-Small-Music-GGUF` \| `stable-audio-3-small-music-f16.gguf`, `stable-audio-3-small-music-q8_0.gguf` \| `stable_audio` \| Stability AI Community License \|
	\| `Stable-Audio-3-Small-SFX-GGUF` \| `stable-audio-3-small-sfx-f16.gguf`, `stable-audio-3-small-sfx-q8_0.gguf` \| `stable_audio` \| Stability AI Community License \|
	\| `Supertonic-3-GGUF` \| `supertonic-3-orig.gguf`, `supertonic-3-f16.gguf`, `supertonic-3-q8_0.gguf` \| `supertonic` \| BigScience Open RAIL-M \|
	\| `Vevo2-GGUF` \| `vevo2-orig.gguf`, `vevo2-f16.gguf`, `vevo2-q8_0.gguf` \| `vevo2` \| See original model package \|
	\| `VibeVoice-ASR-GGUF` \| `vibevoice-asr-f16.gguf`, `vibevoice-asr-q8_0.gguf` \| `vibevoice_asr` \| MIT \|
	\| `VoxCPM2-GGUF` \| `voxcpm2-orig.gguf`, `voxcpm2-bf16.gguf`, `voxcpm2-q8_0.gguf` \| `voxcpm2` \| Apache-2.0 \|
	\| `Voxtral-Mini-4B-Realtime-2602-GGUF` \| `voxtral-mini-4b-realtime-2602-bf16.gguf`, `voxtral-mini-4b-realtime-2602-q8_0.gguf` \| `voxtral_realtime` \| Apache-2.0 \|

	## Usage

	Pass a GGUF file directly as `--model`:

	```bash
	audiocpp_cli --task tts --family supertonic --model Supertonic-3-GGUF/supertonic-3-orig.gguf --backend cuda --language en --text "Hello." --voice-id M1 --out out.wav
	```

	For ASR:

	```bash
	audiocpp_cli --task asr --family qwen3_asr --model Qwen3-ASR-0.6B-GGUF/qwen3-asr-0.6b-f16.gguf --backend cuda --audio speech.wav --text "" --text-out transcript.txt
	```

	## License

	Each GGUF file is a converted form of its original model. Use and redistribution are governed by the corresponding original model license listed above. Please review the original model card and license terms before using or redistributing any converted weights.