The ultimate training toolkit for finetuning diffusion models

A unified inference and post-training framework for accelerated video generation.

let's see what you've been saying and who you've been talking to

Generate long Sora 2 videos that exceed OpenAI's native 12-second limit

Beads - A memory upgrade for your coding agent

Text-audio foundation model from Boson AI

Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- H…

Foundational Models for State-of-the-Art Speech and Text Translation

Kura is a simple reproduction of the CLIO paper which uses language models to label user behaviour before clustering them based on embeddings recursively. This helps us understand user behaviour on…

Claude Code SDK Demos

Get your documents ready for gen AI

structured outputs for llms

Easily train a good VC model with voice data <= 10 mins!

VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design

Instant voice cloning by MIT and MyShell. Audio foundation model.

Inference at the speed of light.

A comprehensive 0-to-1 guide for building self-improving LLM applications with DSPy framework

Prefect is a workflow orchestration framework for building resilient data pipelines in Python.

Optimize prompts, code, and more with AI-powered Reflective Optimization

Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ builders.

Open-source platform to build and deploy AI agent workflows.

Generate SDKs and docs for your API

Version control system for any file format

Open source conversation framework for structured Pipecat dialogues

Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.

Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.