aufklarer/Silero-VAD-v5-MLX
Voice Activity Detection • 309k • Updated • 32.1k • 3
MLX Speech Models
Speech AI models for Apple Silicon via MLX. ASR, TTS, VAD, diarization, speaker embedding.
-
-
aufklarer/WeSpeaker-ResNet34-LM-MLX
Audio Classification • 6.63M • Updated • 24.9k • 4 -
aufklarer/Silero-VAD-v6.2.1-MLX
Audio Classification • 309k • Updated • 15.2k • 1 -
aufklarer/Qwen3-ASR-1.7B-MLX-8bit
2B • Updated • 7.38k • 5 -
aufklarer/Qwen3-ASR-0.6B-MLX-4bit
0.8B • Updated • 5.73k • 5 -
aufklarer/Qwen3-ForcedAligner-0.6B-4bit
Audio Classification • 0.4B • Updated • 5.26k • 1 -
aufklarer/Pyannote-Segmentation-MLX
Voice Activity Detection • 1.49M • Updated • 4.67k • 2 -
aufklarer/Qwen3-ASR-0.6B-MLX-8bit
0.8B • Updated • 1.19k • 1 -
aufklarer/Higgs-TTS-3-4B-MLX-bf16
Text-to-Speech • 5B • Updated • 307 -
aufklarer/PersonaPlex-7B-MLX-4bit
Audio-to-Audio • Updated • 388 • 43 -
aufklarer/Qwen3.5-0.8B-Chat-MLX
Text Generation • Updated • 680 • 1 -
aufklarer/Qwen3-4B-Instruct-2507-MLX-4bit
Text Generation • 4B • Updated • 609 • 1
aufklarer/MADLAD400-3B-MT-MLX
Translation • Updated • 73Note Many-to-many translation across 400+ languages (T5 v1.1, INT4/INT8).
-
aufklarer/Qwen3-TTS-12Hz-0.6B-Base-MLX-4bit
0.9B • Updated • 131 -
aufklarer/CosyVoice3-0.5B-MLX-4bit
Text-to-Speech • Updated • 287 -
aufklarer/Qwen3-ASR-1.7B-MLX-4bit
Automatic Speech Recognition • 0.9B • Updated • 645 • 3 -
aufklarer/Magpie-TTS-Multilingual-357M-MLX-4bit
Text-to-Speech • Updated • 112 -
aufklarer/PersonaPlex-7B-MLX-8bit
Audio-to-Audio • Updated • 185 • 14 -
aufklarer/Qwen3-ForcedAligner-0.6B-8bit
Audio Classification • 0.5B • Updated • 111 -
aufklarer/Qwen3-ForcedAligner-0.6B-bf16
Audio Classification • 0.9B • Updated • 27 -
aufklarer/Qwen3-TTS-12Hz-1.7B-Base-MLX-8bit
0.8B • Updated • 80 -
aufklarer/Qwen3-TTS-12Hz-0.6B-CustomVoice-MLX-4bit
0.9B • Updated • 130 -
aufklarer/Qwen3-TTS-12Hz-1.7B-Base-MLX-4bit
0.6B • Updated • 45 -
aufklarer/Qwen3-TTS-12Hz-0.6B-Base-MLX-8bit
0.5B • Updated • 291 • 1 -
aufklarer/Omnilingual-ASR-CTC-7B-MLX-8bit
Automatic Speech Recognition • 7B • Updated • 21 -
aufklarer/Omnilingual-ASR-CTC-300M-MLX-4bit
Automatic Speech Recognition • 0.3B • Updated • 53 -
aufklarer/Omnilingual-ASR-CTC-3B-MLX-8bit
Automatic Speech Recognition • 3B • Updated • 33 -
aufklarer/Omnilingual-ASR-CTC-1B-MLX-8bit
Automatic Speech Recognition • 1.0B • Updated • 20 -
aufklarer/Omnilingual-ASR-CTC-3B-MLX-4bit
Automatic Speech Recognition • 3B • Updated • 16 -
aufklarer/OpenUnmix-HQ-MLX
Audio-to-Audio • Updated • 90 • 1 -
aufklarer/Omnilingual-ASR-CTC-7B-MLX-4bit
Automatic Speech Recognition • 7B • Updated • 17 -
aufklarer/Omnilingual-ASR-CTC-1B-MLX-4bit
Automatic Speech Recognition • 1.0B • Updated • 22 -
aufklarer/OpenUnmix-L-MLX
Audio-to-Audio • Updated • 8 -
aufklarer/Omnilingual-ASR-CTC-300M-MLX-8bit
Automatic Speech Recognition • 0.3B • Updated • 12 -
aufklarer/VibeVoice-Realtime-0.5B-MLX-INT4
Text-to-Speech • 0.4B • Updated • 28 -
aufklarer/VibeVoice-Realtime-0.5B-MLX-INT8
Text-to-Speech • 0.5B • Updated • 24 -
aufklarer/VibeVoice-1.5B-MLX-INT4
Text-to-Speech • 0.8B • Updated • 139
aufklarer/CosyVoice3-0.5B-MLX-8bit
Text-to-Speech • Updated • 165Note 8-bit LLM variant — bundled S3-Tokenizer-v3 for zero-shot voice cloning
-
aufklarer/Hibiki-Zero-3B-MLX-4bit
Updated • 7 -
aufklarer/Hibiki-Zero-3B-MLX-8bit
Updated • 11 -
aufklarer/VoxCPM2-MLX-bf16
Text-to-Speech • 2B • Updated • 207 • 1 -
aufklarer/Instruct-MusicGen-MLX-4bit
Text-to-Audio • 0.8B • Updated • 20 -
aufklarer/VoxCPM2-MLX-int4
Text-to-Speech • 2B • Updated • 80 -
aufklarer/VoxCPM2-MLX-int8
Text-to-Speech • 2B • Updated • 204 • 1 -
aufklarer/MAGNeT-Small-30secs-MLX-4bit
Text-to-Audio • 80.6M • Updated • 48 -
aufklarer/MAGNeT-Small-30secs-MLX-8bit
Text-to-Audio • 0.1B • Updated • 10 -
aufklarer/MAGNeT-Medium-30secs-MLX-4bit
Text-to-Audio • 0.3B • Updated • 24 -
aufklarer/MAGNeT-Medium-30secs-MLX-8bit
Text-to-Audio • 0.5B • Updated • 12 -
aufklarer/FlashSR-MLX-4bit
Audio-to-Audio • 0.1B • Updated • 355 -
aufklarer/FlashSR-MLX-8bit
Audio-to-Audio • 0.2B • Updated • 32 -
aufklarer/AudioSR-MLX-4bit
Audio-to-Audio • 0.1B • Updated • 15 -
aufklarer/AudioSR-MLX-8bit
Audio-to-Audio • 0.2B • Updated • 21 -
aufklarer/Magpie-TTS-Multilingual-357M-MLX-8bit
Text-to-Speech • Updated • 363 -
aufklarer/Stable-Audio-3-DiT-Medium-MLX-8bit
Text-to-Audio • Updated • 77 • 1 -
aufklarer/Stable-Audio-3-DiT-Small-Music-MLX-4bit
Text-to-Audio • Updated • 86 • 1 -
aufklarer/CosyVoice3-0.5B-MLX-bf16
Text-to-Speech • Updated • 511 -
aufklarer/Chatterbox-Multilingual-MLX-fp16
Text-to-Speech • 0.6B • Updated • 219 • 1 -
aufklarer/Nemotron-3.5-ASR-Streaming-0.6B-MLX-bf16
Automatic Speech Recognition • 0.6B • Updated • 70 • 3 -
aufklarer/Nemotron-3.5-ASR-Streaming-0.6B-MLX-8bit
Automatic Speech Recognition • 0.6B • Updated • 201 • 4 -
aufklarer/Nemotron-3.5-ASR-Streaming-0.6B-MLX-4bit
Automatic Speech Recognition • 0.6B • Updated • 100 • 4 -
aufklarer/Qwen3-TTS-12Hz-1.7B-Base-MLX-bf16
Text-to-Speech • 2B • Updated • 138 -
aufklarer/Indic-Mio-MLX-fp16
Text-to-Speech • 0.6B • Updated • 61 • 1 -
aufklarer/WavLM-Base-Plus-MLX-fp16
Feature Extraction • 94.4M • Updated • 21 -
aufklarer/Chatterbox-Multilingual-hi-MLX-fp16
Text-to-Speech • 0.6B • Updated • 11 • 1 -
aufklarer/CosyVoice3-0.5B-MLX-8bit-full
Text-to-Speech • Updated • 78 -
aufklarer/Fish-Audio-S2-Pro-MLX-fp16
Text-to-Speech • 5B • Updated • 55 • 1 -
aufklarer/HTDemucs-FT-MLX
Updated • 36 • 1 -
aufklarer/OmniVoice-MLX-fp16
Text-to-Speech • 0.6B • Updated • 38 -
aufklarer/OmniVoice-MLX-int8
Text-to-Speech • 0.6B • Updated • 62 • 1 -
aufklarer/Qwen3-4B-Instruct-2507-MLX-5bit
Text Generation • 4B • Updated • 32 -
aufklarer/Qwen3-ASR-0.6B-MLX-5bit
0.5B • Updated • 29 • 1 -
aufklarer/Qwen3-ASR-1.7B-MLX-5bit
1.0B • Updated • 721 -
aufklarer/Qwen3-TTS-12Hz-0.6B-CustomVoice-MLX-bf16
0.9B • Updated • 130 • 1 -
aufklarer/Stable-Audio-3-DiT-Small-SFX-MLX-4bit
Updated • 2 • 1 -
aufklarer/gemma-4-E2B-it-MLX-2bit
Text Generation • 5B • Updated • 33 -
aufklarer/gemma-4-E2B-it-MLX-4bit
Text Generation • 5B • Updated • 25 -
aufklarer/gemma-4-E4B-it-MLX-2bit
Text Generation • 7B • Updated • 32 -
aufklarer/gemma-4-E4B-it-MLX-4bit
Text Generation • 7B • Updated • 68 • 1 -
aufklarer/Audio2Face-3D-v2.3-Mark-MLX
Updated • 66 • 1 -
aufklarer/Audio2Face-3D-v2.3.1-Claire-MLX
Updated • 27 • 1 -
aufklarer/Audio2Face-3D-v2.3.1-James-MLX
Updated • 34 -
aufklarer/F5TTS-v1-Base-MLX-fp16
Text-to-Speech • 0.3B • Updated • 54 -
aufklarer/MOSS-Transcribe-Diarize-0.9B-MLX-INT8
Automatic Speech Recognition • Updated • 167 • 1 -
aufklarer/Cohere-Transcribe-2B-MLX-FP16
Automatic Speech Recognition • 2B • Updated • 31 -
aufklarer/Cohere-Transcribe-2B-MLX-5bit
Automatic Speech Recognition • 2B • Updated • 40 -
aufklarer/Cohere-Transcribe-2B-MLX-8bit
Automatic Speech Recognition • 2B • Updated • 38 -
aufklarer/Voxtral-Mini-3B-2507-MLX-FP16
Automatic Speech Recognition • 5B • Updated • 26 -
aufklarer/Voxtral-Mini-3B-2507-MLX-5bit
Automatic Speech Recognition • 5B • Updated • 44 -
aufklarer/Voxtral-Mini-3B-2507-MLX-8bit
Automatic Speech Recognition • 5B • Updated • 31 -
aufklarer/CSM-1B-MLX-8bit
Text-to-Speech • 2B • Updated • 18 -
aufklarer/CSM-1B-MLX-5bit
Text-to-Speech • 2B • Updated • 6 -
aufklarer/CSM-1B-MLX-fp16
Text-to-Speech • 2B • Updated • 6 -
aufklarer/Nemotron-3.5-ASR-Streaming-0.6B-MLX-5bit
Automatic Speech Recognition • 0.6B • Updated • 40 -
aufklarer/DeepFilterNet3-MLX
Audio-to-Audio • 2.13M • Updated • 79 -
aufklarer/VoiceChat-11B-Perception-MLX-int8
Audio-to-Audio • Updated • 79 • 1 -
aufklarer/VoiceChat-11B-Perception-MLX-int5
Audio-to-Audio • Updated • 594 • 8 -
aufklarer/SpeechBrain-ECAPA-VoxLingua107-21M-MLX
Audio Classification • 21.3M • Updated • 62 -
aufklarer/SpeechBrain-ECAPA-VoxCeleb-20M-MLX
Feature Extraction • 20.8M • Updated • 27