Make your meetings accessible to AI Agents

Firmware and kernel modules for the Miyoo Flip.

Compilation of BIOSes for various emulation platforms

Make your meetings accessible to AI Agents

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

Full stack, modern web application template. Using FastAPI, React, SQLModel, PostgreSQL, Docker, GitHub Actions, automatic HTTPS and more.

Huly — All-in-One Project Management Platform (alternative to Linear, Jira, Slack, Notion, Motion)

🪓 Run Background Tasks at Scale

SoTA open-source TTS

Model swapping for llama.cpp (or any local OpenAI API compatible server)

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Official implementation of paper AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding

GenAI Agent Framework, the Pydantic way

Transformer with Local Modeling by Convolution for Speech Separation and Enhancement

A TTS model capable of generating ultra-realistic dialogue in one pass.

High-performance Text-to-Speech server with OpenAI-compatible API, 8 voices, emotion tags, and modern web UI. Optimized for RTX GPUs.

A blazing fast AI Gateway with integrated guardrails. Route to 200+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Towards Human-Sounding Speech

Fast job queuing and RPC in python with asyncio and redis.

Uncomplicated Observability for Python and beyond! 🪵🔥

Monitor browser logs directly from Cursor and other MCP compatible IDEs.

Open-Sora: Democratizing Efficient Video Production for All

This repository contains audio samples and supplementary materials accompanying publications by the "Speaker, Voice and Language" team at Google.

Build Real-Time Knowledge Graphs for AI Agents

Convert any PDF into a podcast episode!

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS …

An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI