README.md · audio.cpp-gguf

1

---

2

license: other

3

library_name: audio.cpp

4

pipeline_tag: text-to-speech

5

tags:

6

- gguf

7

- audio.cpp

8

- quantized

9

- text-to-speech

10

- automatic-speech-recognition

11

- voice-conversion

12

- text-to-audio

13

- audio-to-audio

14

- source-separation

15

- speaker-diarization

16

- speech

17

base_model_relation: quantized

18

base_model:

19

- MiniMaxAI/MiniMax-H3

20

- ACE-Step/Ace-Step1.5

21

- ACE-Step/acestep-v15-base

22

- Aratako/Irodori-TTS-500M-v3

23

- Aratako/Irodori-TTS-600M-v3-VoiceDesign

24

- Aratako/Irodori-TTS-v4.1-Small

25

- Aratako/MioCodec-25Hz-44.1kHz-v2

26

- Aratako/MioTTS-1.7B

27

- Aratako/Semantic-DACVAE-Japanese-32dim

28

- Banafo/Kroko-ASR

29

- dots-studio/dots.tts-mf

30

- dots-studio/dots.tts-soar

31

- fishaudio/s2-pro

32

- FunAudioLLM/Fun-ASR-Nano-2512-hf

33

- HeartMuLa/HeartCodec-oss-20260123

34

- HeartMuLa/HeartMuLa-oss-3B

35

- HeartMuLa/HeartMuLaGen

36

- IndexTeam/IndexTTS-2

37

- IndexTeam/IndexTTS-2.5

38

- ASLP-lab/MeanVC2

39

- OpenBMB/VoxCPM2

40

- OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano

41

- OpenMOSS-Team/MOSS-Audio-Tokenizer-v2

42

- OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5

43

- OpenMOSS-Team/MOSS-TTS-Nano-100M

44

- Qwen/Qwen3-ASR-0.6B

45

- Qwen/Qwen3-ASR-1.7B-hf

46

- Qwen/Qwen3-ForcedAligner-0.6B

47

- Qwen/Qwen3-TTS-12Hz-0.6B-Base

48

- Qwen/Qwen3-TTS-12Hz-1.7B-Base

49

- Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

50

- Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign

51

- Qwen/Qwen3-TTS-Tokenizer-12Hz

52

- ResembleAI/chatterbox

53

- RMSnow/Vevo2

54

- bosonai/higgs-audio-v3-stt

55

- bosonai/higgs-audio-v3-tts-4b

56

- k2-fsa/OmniVoice

57

- kyutai/pocket-tts

58

- llm-jp/llm-jp-3-150m

59

- microsoft/VibeVoice-1.5B

60

- microsoft/VibeVoice-ASR

61

- mistralai/Voxtral-Mini-4B-Realtime-2602

62

- mlx-community/SeedVC-MLX

63

- mlx-community/mel-roformer-mlx

64

- mlx-community/supertonic-3-mlx

65

- mlx-community/wavlm-base-plus-mlx

66

- MuScriptor/muscriptor-small

67

- neuphonic/neutts-2e

68

- syvai/hviske-v5.3

69

- nvidia/diar_sortformer_4spk-v1

70

- nvidia/magpie_tts_multilingual_357m

71

- nvidia/nemotron-3.5-asr-streaming-0.6b

72

- nvidia/parakeet-tdt-0.6b-v3

73

- nvidia/personaplex-7b-v1

74

- owensong/Inflect-Micro-v2

75

- stabilityai/stable-audio-3-medium

76

- stabilityai/stable-audio-3-small-music

77

- stabilityai/stable-audio-3-small-sfx

78

---

79

80

# audio.cpp GGUF Model Packages

81

82

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).

83

84

If you enjoy the project, please star [audio.cpp on GitHub](https://github.com/0xShug0/audio.cpp) and this Hugging Face repository.

85

86

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

87

88

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

89

90

!!! 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.

91

92

93

## Files

94

95

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

96

97

98

|---|---|---|---|

99

| `ACE-Step1.5-GGUF` | `ace_step` | BF16 + Q8 | MIT |

100

| `AudioSR-GGUF` | `audiosr` | F32 | MIT |

101

102

103

| `Chatterbox-GGUF` | `chatterbox` | F16 + Q8 | MIT |

104

| `Chatterbox-Turbo-GGUF` | `chatterbox_turbo` | Q8 | MIT |

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

| `HTDemucs-GGUF` | `htdemucs` | F16 + Q8 | MIT |

121

122

123

124

125

126

127

| `Irodori-TTS-500M-v3-GGUF` | `irodori_tts` | F16 + Q8 | MIT |

128

| `Irodori-TTS-600M-v3-VoiceDesign-GGUF` | `irodori_tts` | F16 + Q8 | MIT |

129

| `Irodori-TTS-v4-Small-GGUF` | `irodori_tts` | F16 + Q8 | MIT |

130

131

132

133

134

135

136

137

138

| `Mel-Band-RoFormer-GGUF` | `mel_band_roformer` | F16 + Q8 | MIT |

139

140

141

142

143

| `Moonshine-Streaming-GGUF` | `moonshine_asr` | Q8 | MIT |

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

| `RVC-GGUF` | `rvc` | F16 | MIT |

159

160

161

162

163

164

165

166

167

| `VibeVoice-ASR-GGUF` | `vibevoice_asr` | F16 + Q8 | MIT |

168

169

170

171

172

## Usage

173

174

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

175

176

```bash

177

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

178

```

179

180

For ASR:

181

182

```bash

183

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

184

```

185

186

## License

187

188

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.

189