!!! 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.

audio-cpp/audio.cpp-gguf

audio.cpp GGUF Model Packages

Files

Usage

License

audio-cpp/
audio.cpp-gguf