The open-source AI voice studio. Clone, dictate, create.
-
Updated
Aug 9, 2026 - TypeScript
#
MLX
MLX is a NumPy-like array framework designed for efficient and flexible machine learning on Apple silicon, brought to you by Apple machine learning research.
Here are 2,628 public repositories matching this topic...
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
workflow text-to-speech ai cuda audiobook tts translate speech-to-text transcription mlx tauri dubbing voice-cloning huggingface voice-generation local-first voice-ai elevenlabs-alternative omnivoice-studio voicestudio
-
Updated
Sep 27, 2026 - Python
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
-
Updated
Sep 27, 2026 - Python
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
-
Updated
Aug 26, 2026 - Python
Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.
swift mcp openai mlx llm anthropic apple-neural-engine apple-intelligence mcp-server apple-foundation-models
-
Updated
Sep 27, 2026 - Swift
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
text-to-speech transformers speech-synthesis speech-recognition speech-to-text audio-processing mlx multimodal apple-silicon
-
Updated
Sep 24, 2026 - Python
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
machine-learning inference decision-model mlx laya apple-silicon local-ai modernbert system-one typed-decisions
-
Updated
Sep 22, 2026 - Python
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
mlx vision-framework apple-silicon vision-transformer llm vision-language-model llava local-ai idefics florence2 paligemma pixtral molmo
-
Updated
Sep 26, 2026 - Python
Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 2,200+ medical models, 21 languages, Apple MLX + Python, no cloud, no patient data leaving your network. Apache-2.0
javascript android python nlp swift ios skills healthcare hipaa ner mlx pii on-premise on-device swiftui clinical-nlp pii-detection llm local-llm sovereign-ai
-
Updated
Sep 27, 2026 - Python
The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.
-
Updated
Sep 18, 2026 - Python
Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.
search search-engine video mp4 tesla gemini semantic-search dashcam mlx chromadb qwen3-vl gemini-embedding-2
-
Updated
Sep 25, 2026 - Python
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server and Mac app for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Release-gated with Claude Code, Codex CLI, Aider, Hermes and DeepSeek Harness.
python macos inference-server mlx apple-silicon openai-api llm local-llm llm-inference local-ai qwen llm-server coding-agents continuous-batching tool-calling anthropic-api openai-compatible claude-code ollama-alternative omlx-alternative
-
Updated
Sep 27, 2026 - Python
Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated), Gemma 4 31B, Qwen 3.5 122B (65 tok/s), DeepSeek V4 Flash (1M ctx). Private, offline, airgap-ready. Built for NDA / legal / healthcare workflows.
macos llama airgap gemma mlx on-device-ai ai-privacy voice-ai apple-silicon ambient-computing browser-agent anthropic local-llm local-ai qwen offline-ai private-ai mlx-lm claude-code abliterated
-
Updated
Sep 20, 2026 - Python
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
macos metal mtp mlx inference-engine apple-silicon local-llm llm-inference local-ai qwen speculative-decoding openai-compatible claude-code qwen3-next anthropic-compatible native-mtp mtplx qwen3-8 qwen3-8-flash-next flash-next
-
Updated
Sep 26, 2026 - Python