!!! 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

Tested summarizes the current audio.cpp path-test status. See the GGUF guide above for the full matrix and drift notes.

Directory	Files	audio.cpp family	Tested	Original model license
`ACE-Step1.5-GGUF`	`base/ace-step-1.5-base-bf16.gguf`, `base/ace-step-1.5-base-q8_0.gguf`, `turbo/ace-step-1.5-turbo-bf16.gguf`, `turbo/ace-step-1.5-turbo-q8_0.gguf`	`ace_step`	16-bit + Q8 drift	MIT
`BS-RoFormer-ep368-GGUF`	`bs-roformer-ep368-q8_0.gguf`	`bs_roformer`	Q8 pass	Apache-2.0
`Chatterbox-GGUF`	`chatterbox-f16.gguf`, `chatterbox-q8_0.gguf`	`chatterbox`	16-bit + Q8 ASR-match drift	MIT
`Citrinet-ASR-GGUF`	`citrinet-asr-q8_0.gguf`	`citrinet_asr`	Q8 pass	CC-BY-4.0
`Confucius4-TTS-GGUF`	`confucius4-tts-orig.gguf`	`confucius4_tts`	orig pass	Apache-2.0
`DotTTS-MF-GGUF`	`dots-tts-mf-bf16.gguf`	`dots_tts`	experimental	Apache-2.0
`DotTTS-SOAR-GGUF`	`dots-tts-soar-orig.gguf`, `dots-tts-soar-bf16.gguf`	`dots_tts`	experimental	Apache-2.0
`DramaBox-GGUF`	`dramabox-q8_0.gguf`	`dramabox`	Q8 pass	LTX-2 Community License
`Fish-Audio-S2-Pro-GGUF`	`fish-audio-s2-pro-bf16.gguf`, `fish-audio-s2-pro-q8_0.gguf`	`fish_audio`	16-bit + Q8 pass	Fish Audio Research License
`Fun-ASR-Nano-2512-GGUF`	`fun-asr-nano-2512-f16.gguf`, `fun-asr-nano-2512-q8_0.gguf`	`fun_asr_nano`	16-bit + Q8 pass	FunASR Model Open Source License Agreement v1.1
`HeartMuLa-GGUF`	`heartmula-f16.gguf`, `heartmula-q8_0.gguf`	`heartmula`	16-bit + Q8 drift	Apache-2.0
`HTDemucs-GGUF`	`htdemucs-f16.gguf`, `htdemucs-q8_0.gguf`	`htdemucs`	16-bit pass, Q8 drift	MIT
`Higgs-Audio-v3-STT-GGUF`	`higgs-audio-v3-stt-f16.gguf`, `higgs-audio-v3-stt-q8_0.gguf`	`higgs_audio_stt`	16-bit + Q8 pass	Apache-2.0
`Higgs-Audio-v3-TTS-4B-GGUF`	`higgs-audio-v3-tts-4b-bf16.gguf`, `higgs-audio-v3-tts-4b-q8_0.gguf`	`higgs_audio_tts`	16-bit + Q8 pass	Boson Higgs TTS 3 Research and Non-Commercial License
`Hviske-v5.3-GGUF`	`hviske-v5.3-q8_0.gguf`	`hviske_asr`	Q8 pass	CC-BY-NC-4.0
`IndexTTS2-GGUF`	`index-tts2-orig.gguf`, `index-tts2-f16.gguf`, `index-tts2-q8_0.gguf`	`index_tts2`	orig + 16-bit pass/drift, Q8 ASR-match drift	bilibili Model Use License Agreement
`IndexTTS2.5-GGUF`	`index-tts2_5-orig.gguf`, `index-tts2_5-f16.gguf`, `index-tts2_5-q8_0.gguf`	`index_tts2`	self-contained smoke pass; Q8/F16/orig CUDA load + synthesize	bilibili Model Use License Agreement
`Inflect-Micro-v2-GGUF`	`inflect-micro-v2-orig.gguf`	`inflect_v2`	orig pass	Apache-2.0
`Irodori-TTS-500M-v3-GGUF`	`irodori-tts-500m-v3-f16.gguf`, `irodori-tts-500m-v3-q8_0.gguf`	`irodori_tts`	16-bit pass, Q8 drift	MIT
`Irodori-TTS-600M-v3-VoiceDesign-GGUF`	`irodori-tts-600m-v3-voicedesign-f16.gguf`, `irodori-tts-600m-v3-voicedesign-q8_0.gguf`	`irodori_tts`	16-bit pass, Q8 drift	MIT
`Irodori-TTS-v4-Small-GGUF`	`irodori-tts-v4-small-f16.gguf`, `irodori-tts-v4-small-q8_0.gguf`	`irodori_tts`	v4.1 checkpoint, 16-bit + Q8 pass	MIT
`Kroko-ASR-GGUF`	`kroko-en-community-64-l-q8_0.gguf`	`kroko_asr`	Q8 pass	CC-BY-SA community model license
`MOSS-TTS-Local-v1.5-GGUF`	`moss-tts-local-v1.5-bf16.gguf`, `moss-tts-local-v1.5-q8_0.gguf`	`moss_tts_local`	16-bit pass, Q8 ASR-match drift	Apache-2.0
`MOSS-TTS-Nano-100M-GGUF`	`moss-tts-nano-100m-bf16.gguf`, `moss-tts-nano-100m-q8_0.gguf`	`moss_tts_nano`	16-bit pass, Q8 ASR-match drift	Apache-2.0
`MagpieTTS-Multilingual-357M-GGUF`	`magpie-tts-multilingual-357m-orig.gguf`	`magpie_tts`	experimental	NVIDIA Open Model License
`Mel-Band-RoFormer-GGUF`	`mel-band-roformer-f16.gguf`, `mel-band-roformer-q8_0.gguf`	`mel_band_roformer`	16-bit + Q8 drift	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`	orig pass, 16-bit + Q8 drift	MIT
`MioTTS-1.7B-GGUF`	`miotts-1.7b-orig.gguf`, `miotts-1.7b-bf16.gguf`, `miotts-1.7b-q8_0.gguf`	`miotts`	orig pass, 16-bit drift, Q8 ASR-match drift	Apache-2.0
`MuScriptor-Small-GGUF`	`muscriptor-small-f32.gguf`	`muscriptor`	F32 pass	CC-BY-NC-4.0
`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`	16-bit pass, Q8 minor filler drift	OpenMDW-1.1
`OmniVoice-GGUF`	`omnivoice-bf16.gguf`, `omnivoice-f16.gguf`, `omnivoice-q8_0.gguf`	`omnivoice`	16-bit + Q8 drift	Apache-2.0
`Parakeet-TDT-0.6B-v3-GGUF`	`parakeet-tdt-0.6b-v3-f16.gguf`, `parakeet-tdt-0.6b-v3-q8_0.gguf`	`parakeet_tdt`	16-bit + Q8 pass	CC-BY-4.0
`PocketTTS-GGUF`	`english/`, `german/`, `italian/`, `portuguese/`, `spanish/` each contain `bf16` and `q8_0` GGUFs	`pocket_tts`	16-bit pass, Q8 drift	CC-BY-4.0
`Qwen3-ASR-0.6B-GGUF`	`qwen3-asr-0.6b-f16.gguf`, `qwen3-asr-0.6b-q8_0.gguf`	`qwen3_asr`	16-bit + Q8 pass	Apache-2.0
`Qwen3-ASR-1.7B-GGUF`	`qwen3-asr-1.7b-f16.gguf`, `qwen3-asr-1.7b-q8_0.gguf`	`qwen3_asr`	16-bit + Q8 pass	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`	16-bit + Q8 pass	Apache-2.0
`Qwen3-TTS-12Hz-0.6B-Base-GGUF`	`qwen3-tts-12hz-0.6b-base-bf16.gguf`, `qwen3-tts-12hz-0.6b-base-q8_0.gguf`	`qwen3_tts`	BF16 exact vs safetensors, Q8 ASR-match drift	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_v2.gguf`	`qwen3_tts`	orig pass, 16-bit + Q8 ASR-match drift	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`	16-bit + Q8 ASR-match drift	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`	16-bit + Q8 ASR-match drift	Apache-2.0
`RVC-GGUF`	`rvc-f16.gguf`	`rvc`	F16 pass	MIT
`SeedVC-MLX-GGUF`	`seed-vc-mlx-orig.gguf`, `seed-vc-mlx-f16.gguf`, `seed-vc-mlx-q8_0.gguf`	`seed_vc`	16-bit + Q8 drift	GPL-3.0
`Sortformer-Diar-4spk-v1-GGUF`	`sortformer-diar-4spk-v1-f16.gguf`, `sortformer-diar-4spk-v1-q8_0.gguf`	`sortformer_diar`	16-bit + Q8 pass	CC-BY-NC-4.0
`Stable-Audio-3-Medium-GGUF`	`stable-audio-3-medium-f16.gguf`, `stable-audio-3-medium-q8_0.gguf`	`stable_audio`	16-bit + Q8 drift	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`	16-bit + Q8 drift	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`	16-bit + Q8 drift	Stability AI Community License
`Supertonic-3-GGUF`	`supertonic-3-orig.gguf`, `supertonic-3-f16.gguf`, `supertonic-3-q8_0.gguf`	`supertonic`	F32/orig pass; f16 not tested; Q8 unsupported dtype	BigScience Open RAIL-M
`Vevo2-GGUF`	`vevo2-orig.gguf`, `vevo2-f16.gguf`, `vevo2-q8_0.gguf`	`vevo2`	orig + 16-bit pass/drift; Q8 mixed route drift	CC-BY-NC-ND-4.0
`VibeVoice-1.5B-GGUF`	`vibevoice-1.5b-bf16.gguf`, `vibevoice-1.5b-q8_0.gguf`, `vibevoice-1.5b-q4-ios.gguf`	`vibevoice`	16-bit pass, Q8 drift	MIT
`VibeVoice-ASR-GGUF`	`vibevoice-asr-f16.gguf`, `vibevoice-asr-q8_0.gguf`	`vibevoice_asr`	16-bit + Q8 pass	MIT
`VoxCPM2-GGUF`	`voxcpm2-orig.gguf`, `voxcpm2-bf16.gguf`, `voxcpm2-q8_0.gguf`	`voxcpm2`	orig pass, 16-bit + Q8 ASR-match drift	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-mini-4b-realtime-2602-q4_k.gguf`	`voxtral_realtime`	16-bit + Q8 pass; Q4_K quick check passed	Apache-2.0

Q8 Notes

Chatterbox Q8 is intentionally mixed type. Graph-sensitive scalar, norm, bias, and side tensors stay in non-Q8 types while matmul-compatible weights are quantized.
PocketTTS Q8 keeps the four flow_lm.flow_net.time_embed.*.mlp.{0,2}.weight tensors in Q8 in addition to the default converter selection. conditioner.embed, cond_embed, and Mimi conv tensors are not forced to Q8 because tested outputs drifted or the current conv path casts quantized conv weights back to F32.
Voxtral Q4_K is smaller than Q8_0 and was faster in a quick CUDA path check, with transcripts matching Q8_0 except for one capitalization-only difference.

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.

saxyZ/audio.cpp-gguf-fork

audio.cpp GGUF Model Packages

Files

Q8 Notes

Usage

License

saxyZ/
audio.cpp-gguf-fork