A TTS that fits in your CPU (and pocket)

A lightning fast audio upsampler.

Fast audio super resolution from 16khz to 48khz.

On-device TTS model by Neuphonic

A package for NeuCodec: a 50hz, 0.8kbps, 24kHz audio codec.

Blazing-fast rust implementation of Sesame's Conversational Speech Model (CSM)

Spark-TTS Inference Code

LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

Interface for OuteTTS models.

A benchmark to evaluate language models on questions I've previously asked them to solve.

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discr…

A gorgeous theme for Tkinter/ttk, based on the Sun Valley visual style ✨

A TensorFlow based wake word detection training framework using synthetic sample generation suitable for certain microcontrollers.

wake word engine benchmark framework

Detect wake words for ESPHome's voice assistant component on the device

Community Collection of Wake-Words for Home Assistant

Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment

Compare the performance of different LLM that can be deployed locally on consumer hardware. Run yourself with Colab WebUI.

Fast & more realistic evaluation of chat language models. Includes leaderboard.

Cross-Platform module to get info on and control windows on screen

openWakeWord for Rhasspy

C++ version of openWakeWord

A fast, local neural text to speech system

A terminal client for Miniflux RSS reader

OpenVoiceOS Core, the FOSS Artificial Intelligence platform.

Python bindings of speexdsp noise suppression library

Python binding for Speex AEX

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)