mlx-audio
Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
Text to speech model, used with mlx-audio.
- 38
- 11k
- apache-2.0
- 10 mo ago
nemotron-3.5-asr-streaming-0.6b
Automatic speech recognition model, used with mlx-audio.
- 18
- 1.3k
- other
- 6 mo ago
Qwen3-TTS-12Hz-0.6B-CustomVoice-8bit
Text to speech model, used with mlx-audio.
- 17
- 8.9k
- apache-2.0
- 10 mo ago
Voxtral-Mini-4B-Realtime-2602-4bit
Automatic speech recognition model, used with mlx.
- 17
- 2k
- apache-2.0
- 10 mo ago
Qwen3-TTS-12Hz-1.7B-VoiceDesign-8bit
Text to speech model, used with mlx-audio.
- 10
- 9.3k
- apache-2.0
- 10 mo ago
Qwen3-ASR-0.6B-8bit
- 6
- 174k
- apache-2.0
- 10 mo ago
mlx-porting-skill
MLX Porting Toolkit — an agent-guided, evidence-gated pipeline (scaffold → convert → parity → benchmark) plus a portable skill for porting PyTorch/Hugging Face models to Apple MLX.
- 5
- Python
- Apache-2.0
- 17 h ago
diar_streaming_sortformer_4spk-v2.1-fp16
Voice activity detection model, used with mlx-audio.
- 2
- 964
- 9 mo ago
granite-speech-intelligence
Local English speech-to-text on Apple Silicon, all on MLX: IBM Granite Speech 5.0 TurboCTC with Silero VAD timestamps, plus on-device summaries and yes/no questions from Granite 4.2, in a Streamlit app.
- 1
- Python
- Apache-2.0
- 13 d ago

