The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
🎙️ Voix et audio
Reconnaissance vocale, synthèse vocale, clonage de voix et génération de musique
Tout 1045🧠 Grands modèles de langage 24🤖 Agents IA 162🧩 Plateformes de développement d’applications 22📚 RAG et bases de connaissances 48💬 Interfaces de chat et clients 40🖥️ Inférence et déploiement en local 88👨💻 Programmation assistée par IA 97🛠️ Frameworks et SDK 47🔌 MCP et écosystème d’outils 36🎨 Génération d’images 26🎬 Génération de vidéo 17🎙️ Voix et audio 45👁️ Vision par ordinateur 26📄 Analyse de documents et scraping 25🗄️ Bases de données vectorielles 25🏋️ Entraînement, fine-tuning et MLOps 71🧪 Évaluation, observabilité et sécurité 79🚪 Passerelles et proxys d’API 12🔎 Recherche et deep research 15⚙️ Bibliothèques de deep learning 58🏷️ Données et annotation 32🔬 IA pour l’industrie et la science 34⚡ Outils de productivité 16
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingu
YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.
A PyTorch-based Speech Toolkit
实时语音对话模型，全双工低延迟。
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
神经网络说话人分离工具包。
A TTS that fits in your CPU (and pocket)
多语言语音识别、情感识别与事件检测一体模型。
仅 82M 参数的开源 TTS，质量出众。
Transcribe on your own!
An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS
Generative models for conditional audio generation
A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, AudioGen, MusicGen, To
ggml speech-to-text inference for 16+ model families
Magenta RealTime 2: An Open-Weights Live Music Model
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
AuK: An Open-Source Foundational Model for Speech Generation and Editing
Whisper command line client compatible with original OpenAI client based on CTranslate2.
AI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.
Jarvis AI Assistant - Voice-powered AI assistant for Mac