Neywa-Labs/mlx-audio
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.
Thành tựu nổi bật
Những danh hiệu mới nhất của dự án
#1 Repository Của Ngày
#1 Repository Của Ngày
#1 Repository Của Ngày
🎧 mlx-audio: Local audio AI for Apple Silicon
One engine for TTS, STT, speech-to-speech, and music generation on Mac.
mlx-audio is Python library from Neywa Labs built on Apple's MLX framework. Runs text-to-speech, speech-to-text, speech-to-speech, and music generation efficiently on Apple Silicon. Offers CLI, Python API, web interface, OpenAI-compatible REST API, and Swift package for iOS/macOS integration.
✨ Highlights
- Apple Silicon optimized: Fast inference tuned for M-series chips with MLX.
- Multi-task audio: Supports TTS, STT, STS, and music generation in one library.
- Flexible interfaces: Use command line, Python API, interactive web UI with 3D audio visualization, or OpenAI-compatible REST API.
- Voice control: Multilingual models, voice customization/cloning, and adjustable speech speed (per README features).
- Quantization support: 3-bit, 4-bit, 6-bit, 8-bit, and more for optimized performance.
- Streaming and output options: CLI supports
--play,--stream,--save,--join_audio, and output path control. - Swift integration: Swift package enables iOS/macOS app integration.
- Example model support: README lists models like Kokoro, KittenTTS, and Qwen3-TTS across languages and repos.
💡 Why it matters
mlx-audio gives single local stack for many speech/audio tasks instead of separate tools per model type. Good fit for Mac developers who want on-device inference, quick prototyping through CLI/API, or app integration through Swift.
Quantization, streaming, and server/UI options make it practical for both experiments and product workflows on Apple Silicon.
#MLX #AppleSilicon #TTS #STT #TiniX
Dự án tương tự
Khám phá các dự án và mô hình AI khác có sự tương đồng.
Qwen3.8-27B-Uncensored-MLX An abliterated (refusal-removed) MLX build of Qwen's Qwen3.8-27B — 2 / 4 / 6 / 8-bit for Apple Silicon One Gateway. Every Model. — Route Smarter · Ship Safer · Spend Less. Website · Model Catalog · Model API · GitHub · Dis...
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
all-MiniLM-L6-v2 This is a sentence-transformers(https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. Usage (Sentence-Transformers) Using t...
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
利用 AI 大模型和自动化工作流,根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.