Vogent Turn: fast, open-source turn-detection for Voice AI applications

SoulX-Podcast is an inference codebase by the Soul AI team for generating high-fidelity podcasts from text.

Long-form streaming TTS system for multi-speaker dialogue generation

Awesome Neural Codec Models, Text-to-Speech Synthesizers & Speech Language Models

A Conversational Speech Generation Model

Create Videos with Code

Mellea is a library for writing generative programs.

Simple MCP-UI widgets for common use cases.

AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.

🤖 WebMCP 🧪

UI over MCP. Create next-gen UI experiences with the protocol and SDK!

Example apps for the Apps SDK

On-device TTS model by Neuphonic

Bringing the power of MCP to the web

MiMo-Audio: Audio Language Models are Few-Shot Learners

Build an email assistant with human-in-the-loop and memory

Chat with your Letta agents over a low-latency voice connection. Advanced voice mode, but with advanced memory.

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Andr…

[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching

Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation.

State-of-the-art TTS model under 25MB 😻

SOTA Open Source TTS

Interface for OuteTTS models.

Fast and local neural text-to-speech engine

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

Next Generation Agentic Proxy for AI Agents and MCP servers

A lightweight end-of-utterance detection model fine-tuned on SmolLM2-135M, optimized for Raspberry Pi and low-power devices.