audio-cpp/audio.cpp-gguf

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.

If you enjoy the project, please star audio.cpp on GitHub and this Hugging Face repository.

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

!!! Converted and quantized packages are checked with automated metrics, but perceived quality can still differ for human listeners. Please validate the exact package, backend, and route to confirm the output is acceptable for your use case.

Files

The table lists the GGUF packages currently provided by this repository.

Directory	audio.cpp family	GGUF provided	Original model license
ACE-Step1.5-GGUF	ace_step	BF16 + Q8	MIT
AudioSR-GGUF	audiosr	F32	MIT
BS-RoFormer-ep368-GGUF	bs_roformer	Q8	Apache-2.0
Chatterbox-GGUF	chatterbox	F16 + Q8	MIT
Citrinet-ASR-GGUF	citrinet_asr	Q8	CC-BY-4.0
Confucius4-TTS-GGUF	confucius4_tts	original	Apache-2.0
ControlFoley-GGUF	controlfoley	F32	Apache-2.0
DotTTS-Edit-GGUF	dots_tts	BF16 + Q8	Apache-2.0
DotTTS-MF-GGUF	dots_tts	BF16	Apache-2.0
DotTTS-SOAR-GGUF	dots_tts	original + BF16	Apache-2.0
DramaBox-GGUF	dramabox	Q8	LTX-2 Community License
Fish-Audio-S2-Pro-GGUF	fish_audio	BF16 + Q8	Fish Audio Research License
Fun-ASR-Nano-2512-GGUF	fun_asr_nano	F16 + Q8	FunASR Model Open Source License Agreement v1.1
HeartMuLa-GGUF	heartmula	F16 + Q8	Apache-2.0
HTDemucs-GGUF	htdemucs	F16 + Q8	MIT
Higgs-Audio-v3-STT-GGUF	higgs_audio_stt	F16 + Q8	Apache-2.0
Higgs-Audio-v3-TTS-4B-GGUF	higgs_audio_tts	BF16 + Q8	Boson Higgs TTS 3 Research and Non-Commercial License
Hviske-v5.3-GGUF	hviske_asr	Q8	CC-BY-NC-4.0
IndexTTS2-GGUF	index_tts2	original + F16 + Q8	bilibili Model Use License Agreement
IndexTTS2.5-GGUF	index_tts2	original + F16 + Q8	bilibili Model Use License Agreement
Inflect-Micro-v2-GGUF	inflect_v2	original	Apache-2.0
Irodori-TTS-500M-v3-GGUF	irodori_tts	F16 + Q8	MIT
Irodori-TTS-600M-v3-VoiceDesign-GGUF	irodori_tts	F16 + Q8	MIT
Irodori-TTS-v4-Small-GGUF	irodori_tts	F16 + Q8	MIT
Kroko-ASR-GGUF	kroko_asr	Q8	CC-BY-SA community model license
MMS-Forced-Aligner-GGUF	mms_forced_aligner	F16	CC-BY-NC-4.0
MOSS-TTS-Local-v1.5-GGUF	moss_tts_local	BF16 + Q8	Apache-2.0
MOSS-TTS-Nano-100M-GGUF	moss_tts_nano	BF16 + Q8	Apache-2.0
MOSS-VoiceGenerator-GGUF	moss_voicegen	BF16 + F16 codec decode	Apache-2.0
MagpieTTS-Multilingual-357M-GGUF	magpie_tts	original	NVIDIA Open Model License
MeanVC2-GGUF	meanvc2	F32 + Q4_K	Apache-2.0
Mel-Band-RoFormer-GGUF	mel_band_roformer	F16 + Q8	MIT
MiniMax-H3-Q4-GGUF	minimax_h3	Q4_K + INT8 DiT option	MiniMax-H3 Community License
MioCodec-25Hz-44.1kHz-v2-GGUF	miocodec	original + F16 + Q8	MIT
MioTTS-1.7B-GGUF	miotts	original + BF16 + Q8	Apache-2.0
MuScriptor-Small-GGUF	muscriptor	F32	CC-BY-NC-4.0
Nemotron-3.5-ASR-Streaming-0.6B-GGUF	nemotron_asr	F16 + Q8	OpenMDW-1.1
NeuTTS-2E-GGUF	neutts	original	Apache-2.0
OmniVoice-GGUF	omnivoice	BF16 + F16 + Q8	Apache-2.0
Parakeet-TDT-0.6B-v3-GGUF	parakeet_tdt	F16 + Q8	CC-BY-4.0
PersonaPlex-GGUF	personaplex	Q4_K + Q8	Apache-2.0
PocketTTS-GGUF	pocket_tts	BF16 + Q8	CC-BY-4.0
Qwen3-ASR-0.6B-GGUF	qwen3_asr	F16 + Q8	Apache-2.0
Qwen3-ASR-1.7B-GGUF	qwen3_asr	F16 + Q8	Apache-2.0
Qwen3-ForcedAligner-0.6B-GGUF	qwen3_forced_aligner	F16 + Q8	Apache-2.0
Qwen3-TTS-12Hz-0.6B-Base-GGUF	qwen3_tts	BF16 + Q8	Apache-2.0
Qwen3-TTS-12Hz-1.7B-Base-GGUF	qwen3_tts	original + BF16 + Q8	Apache-2.0
Qwen3-TTS-12Hz-1.7B-CustomVoice-GGUF	qwen3_tts	BF16 + Q8	Apache-2.0
Qwen3-TTS-12Hz-1.7B-VoiceDesign-GGUF	qwen3_tts	BF16 + Q8	Apache-2.0
RVC-GGUF	rvc	F16	MIT
SeedVC-MLX-GGUF	seed_vc	original + F16 + Q8	GPL-3.0
Sortformer-Diar-4spk-v1-GGUF	sortformer_diar	F16 + Q8	CC-BY-NC-4.0
Stable-Audio-3-Medium-GGUF	stable_audio	F16 + Q8	Stability AI Community License
Stable-Audio-3-Small-Music-GGUF	stable_audio	F16 + Q8	Stability AI Community License
Stable-Audio-3-Small-SFX-GGUF	stable_audio	F16 + Q8	Stability AI Community License
Supertonic-3-GGUF	supertonic	original + F16 + Q8	BigScience Open RAIL-M
Vevo2-GGUF	vevo2	original + F16 + Q8	CC-BY-NC-ND-4.0
VibeVoice-1.5B-GGUF	vibevoice	BF16 + Q8 + Q4	MIT
VibeVoice-ASR-GGUF	vibevoice_asr	F16 + Q8	MIT
VoxCPM2-GGUF	voxcpm2	original + BF16 + Q8	Apache-2.0
Voxtral-Mini-4B-Realtime-2602-GGUF	voxtral_realtime	BF16 + Q8 + Q4_K	Apache-2.0

Usage

Pass a GGUF file directly as --model:

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:

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.