Tag

MLX Examples

Collection of runnable model implementations — LLaMA, Mistral, Stable Diffusion, Whisper, CLIP, plus LoRA fine-tuning — ported to the MLX array framework so they run natively on Apple silicon's unified memory rather than CUDA.

LiveKit Agents

Builds realtime voice AI agents that run as server-side participants in WebRTC rooms — mix STT, LLM, and TTS providers or use one realtime model. Adds semantic turn detection, SIP telephony, multi-agent handoffs, and an LLM-judge test harness.

Pipecat

Builds real-time voice and multimodal AI agents as composable streaming pipelines. Vendor-neutral: swap among 20+ STT, 20+ LLM and 30+ TTS providers over WebRTC or WebSockets, and compose multi-agent systems with handoff and parallel workers.

Call Center AI

Lets AI agents place and answer business phone calls, holding spoken conversations to collect structured data, answer questions, and escalate to humans. Built on Azure Communication Services and Azure OpenAI, with RAG over your own documents.

GPT-SoVITS-WebUI

Clones a voice from a 5-second sample for zero-shot TTS, or fine-tunes on ~1 minute of audio for few-shot synthesis. Covers Chinese, English, Japanese, Korean, and Cantonese, with a WebUI bundling vocal separation, ASR, and dataset labeling.

ebook2audiobook

Converts e-books (epub, pdf, mobi, docx, and more) into chapter-aware audiobooks, with optional zero-shot voice cloning. Bundles eight TTS engines including XTTSv2 and Bark, and covers 1,158 languages via Meta's MMS — all runnable on CPU or GPU.

MiniCPM-o

Runs GPT-4o-class vision, speech, and full-duplex audio-video conversation on a 9B model small enough to deploy on phones and tablets. The 4.5 release scores 77.6 on OpenCompass and adds real-time bilingual voice with voice cloning.

Gemini-API

Asynchronous, reverse-engineered Python API for programmatic access to the Google Gemini web app — supports persistent cookie auth, streaming text, image/video/audio generation, deep-research workflows, model selection, and a CLI for automation and chatbots.

MoneyPrinterV2

Automates online monetization workflows—generating and scheduling YouTube Shorts, posting to X (Twitter), running affiliate campaigns, and outreach. Modular provider-based design (TTS, LLM hooks, CRON scheduler) and configurable pipelines; legal/ToS risks mean use with caution.

omi

Continuously captures your screen and spoken conversations, transcribes them in real time, generates summaries and action items, and exposes a memory-backed chat that can retrieve what you've seen and heard. Works across desktop, mobile and wearable devices and supports local SDKs and cloud sync.

MLX-VLM

Provides local inference, fine-tuning, and a server/CLI for vision–language and omni (image/audio/video) models via MLX. Supports multi-image chat, audio/video inputs, activation quantization (CUDA), TurboQuant KV cache, and LoRA/QLoRA fine-tuning for on-device workflows.

OmniParse

Ingests documents, images, audio, video and web pages and converts them into structured, LLM-friendly markdown and parsed data. Runs locally (fits on a T4 GPU), supports ~20 file types, offers OCR, transcription, table extraction and a Gradio UI; deployable via Docker/Skypilot. Licensed under GPL-3.0; some model weights carry cc-by-nc-sa restrictions for commercial use.