25 results
- PrivateGPT Featuredrag-documentSecure document Q&A system designed for sensitive data with no internet connection required for full operation.Medium setupCPU OnlyCommercial useApache 2.0★ 58kUpdated 1mo ago
- RAGFlow Featuredrag-documentRAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs.Medium setupCPU OnlyCommercial useApache 2.0★ 81kUpdated 25d ago
- Whisper (OpenAI) Featuredspeech-to-textOpenAI robust speech recognition model supporting 99 languages with near-human accuracy for offline transcription.Medium setupCPU OnlyCommercial useMIT★ 72kUpdated 7mo ago
- whisper.cpp Featuredspeech-to-textLightweight C/C++ port of Whisper for efficient CPU-based transcription without Python dependencies.Low setupCPU OnlyCommercial useMIT★ 38kUpdated 28d ago
- Bark (Suno) Featuredtext-to-speechTransformer-based TTS model generating expressive speech with emotion, music, and sound effects from text prompts.Medium setupCPU OnlyCommercial useMIT★ 31kUpdated 6mo ago
- ComfyUI Featuredimage-generationNode-based Stable Diffusion interface enabling complex image generation workflows with full offline control.Medium setupNVIDIA GPU (CUDA)Commercial useGPL 3.0★ 62kUpdated 26d ago
- FLUX.1 (Black Forest Labs) Featuredimage-generationOpen-weight image generation model with superior prompt adherence and photorealistic output under Apache 2.0 license.Medium setupNVIDIA GPU (CUDA)Commercial useApache 2.0★ 24kUpdated 1mo ago
- Fooocus Featuredimage-generationSimplified Stable Diffusion interface with proprietary inpainting and style controls for high-quality offline generation.Medium setupNVIDIA GPU (CUDA)Commercial useGPL 3.0★ 42kUpdated 1mo ago
- Haystack (Deepset)rag-documentProduction-ready framework for building RAG and search systems with pipeline architecture and built-in evaluation tools.Medium setupCPU OnlyCommercial useApache 2.0★ 18kUpdated 27d ago
- Markerrag-documentFast document converter transforming PDFs, EPUBs, and MOBI files into accurate markdown for LLM ingestion.Medium setupCPU OnlyCommercial useGPL / LGPL★ 22kUpdated 1mo ago
- txtairag-documentOpen-source vector database and search engine with built-in embeddings, ML pipelines, and RAG capabilities.Medium setupCPU OnlyCommercial useApache 2.0★ 10kUpdated 1mo ago
- Unstructuredrag-documentOpen-source document preprocessing library extracting and transforming 40+ file types for downstream LLM applications.Medium setupCPU OnlyCommercial useApache 2.0★ 12kUpdated 27d ago
- faster-whisperspeech-to-textCTranslate2-based Whisper reimplementation up to 4x faster with less memory, enabling efficient offline transcription.Medium setupCPU OnlyCommercial useMIT★ 8.5kUpdated 1mo ago
- NeMo (NVIDIA)speech-to-textNVIDIA conversational AI toolkit for building custom ASR, TTS, and NLP models with enterprise-grade offline deployment.Medium setupNVIDIA GPU (CUDA)Commercial useApache 2.0★ 9.5kUpdated 27d ago
- Silero VADspeech-to-textLightweight voice activity detection model for filtering silence from audio before offline transcription processing.Low setupCPU OnlyCommercial useMIT★ 6.8kUpdated 1mo ago
- SpeechBrainspeech-to-textPyTorch-based speech toolkit supporting ASR, speaker recognition, and audio classification for offline audio pipelines.Medium setupCPU OnlyCommercial useApache 2.0★ 8.2kUpdated 1mo ago
- Voskspeech-to-textOffline speech recognition toolkit designed for edge devices, running on Raspberry Pi with real-time processing.Low setupCPU OnlyCommercial useApache 2.0★ 10kUpdated 2mo ago
- ChatTTStext-to-speechConversational TTS model optimized for dialogue with natural prosody and emotional expression for offline voice generation.Medium setupCPU OnlyAGPL 3.0★ 24kUpdated 1mo ago
- Coqui TTStext-to-speechDeep learning TTS toolkit with voice cloning from 6 seconds of audio and cross-language voice transfer.Medium setupCPU OnlyCommercial useGPL / LGPL★ 14kUpdated 4mo ago
- Fish Speechtext-to-speechMultilingual TTS model with zero-shot voice cloning and high-quality speech synthesis under Apache 2.0 license.Medium setupNVIDIA GPU (CUDA)Commercial useApache 2.0★ 12kUpdated 1mo ago
- Kokorotext-to-speechCompact 82M parameter TTS model with 860+ community voices, fast generation, and Apache 2.0 license.Medium setupCPU OnlyCommercial useApache 2.0★ 9.2kUpdated 1mo ago
- OpenVoice (MyShell)text-to-speechInstant voice cloning framework generating natural speech with fine-grained voice style control for private TTS.Medium setupCPU OnlyCommercial useApache 2.0★ 19kUpdated 2mo ago
- Pipertext-to-speechFast local neural TTS engine optimized for Raspberry Pi and low-resource devices with 20+ language voices.Low setupCPU OnlyCommercial useMIT★ 11kUpdated 6mo ago
- DiffusionBeeimage-generationSimplest way to run Stable Diffusion on Apple Silicon Macs with one-click install and no configuration needed.Medium setupApple Silicon (Metal)Commercial useMIT★ 11kUpdated 2mo ago
- Draw Thingsimage-generationNative macOS and iOS Stable Diffusion client running entirely on-device with Apple Metal acceleration.Medium setupApple Silicon (Metal)Commercial useGPL 3.0★ 5.2kUpdated 1mo ago
Offgrid AI tools · Updated daily
Enclavetools
Stop paying for AI APIs. Everything here runs on your hardware.
Sponsor
Reach 50,000+ enterprise buyers looking for private AI solutions.
Newsletter
5 new tools, every Friday
No fluff. No spam. Join 12,000+ builders.
Get featured
Put your tool at the top
Featured listings get 10× more clicks and are shown prominently across the directory.