Open-source speech-processing software
556 open-source libraries, tools and applications tagged speech-processing, ranked by how closely speech-processing is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.
556 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| NVIDIA-NeMo/Speech NVIDIA NeMo Speech is an open‑source Python toolkit for building, training, and deploying speech AI models such as automatic speech recogni… | 95 | 18521 | active |
| Fay Digital Human Framework Fay is an open-source Python digital human framework that connects 2.5D/3D/mobile/web digital humans or OpenAI-compatible LLMs to business … | 75 | 13549 | active |
| RunAnywhere RunAnywhere is a set of cross-platform SDKs (Swift, Kotlin, React Native, Flutter, TypeScript, C++) over a shared C++ core for running AI m… | 86 | 10332 | active |
| xorbitsai/inference Xinference is an open-source model serving platform for deploying LLMs, embedding, speech, image, and multimodal models via a unified OpenA… | 93 | 9623 | active |
| modelscope/modelscope ModelScope is a Python library and ecosystem built on the 'Model-as-a-Service' concept, providing unified APIs to download, run inference o… | 96 | 9149 | active |
| duixcom/Duix-Mobile Duix Mobile is an open-source SDK for building real-time interactive AI avatars (digital humans) that run on-device on Android, iOS, tablet… | 63 | 8267 | active |
| fonoster/fonoster Fonoster is an open-source programmable telecommunications stack (a Twilio alternative) for building voice and messaging applications, with… | 98 | 8142 | active |
| vLLM vLLM-Omni is a Python framework extending vLLM for efficient inference and serving of omni-modality models, including diffusion transformer… | 84 | 7293 | active |
| facebookresearch/fairseq Fairseq is a PyTorch-based sequence modeling toolkit from Facebook AI Research for training custom models for translation, summarization, l… | 10 | 32211 | maintenance |
| Shaunwei/RealChar RealChar is an open-source application for creating, customizing, and talking to AI characters/companions in realtime via voice or text. It… | 45 | 6211 | active |
| Cactus Cactus is a hybrid edge-cloud AI inference engine for mobile devices, wearables, smart home devices, and robots, built in C++ with custom q… | 85 | 6111 | active |
| AidLux (AidLearning) AidLux (originally AidLearning) is an AIoT development platform that runs a native Ubuntu Linux environment with GUI, deep learning tooling… | 63 | 5812 | active |
| pytorch/executorch ExecuTorch is PyTorch's framework for exporting and running AI models on-device across mobile, embedded, and edge hardware, with a tiny (~5… | 94 | 5113 | active |
| OpenNMT/CTranslate2 CTranslate2 is a C++ and Python library for fast, memory-efficient inference of Transformer models on CPU and GPU. It uses quantization, la… | 94 | 4684 | stable |
| tensorflow/tensor2tensor Tensor2Tensor (T2T) is a Python library of deep learning models and datasets built on TensorFlow, developed by the Google Brain team to mak… | 10 | 17473 | maintenance |
| OpenAvatarChat OpenAvatarChat is a modular interactive digital human (talking avatar) chat application that combines ASR, LLM, TTS, and avatar rendering c… | 69 | 3802 | active |
| PeterH0323/Streamer-Sales Streamer-Sales is a fine-tuned LLM-based AI sales livestreamer application that generates persuasive product commentary from product descri… | 17 | 3775 | active |
| datascale-ai/opentalking OpenTalking is an open-source Python framework for building real-time AI digital-human (talking avatar) conversation products. It orchestra… | 61 | 3131 | active |
| sonos/tract Tract is Sonos' tiny, self-contained neural-network inference engine written in Rust. It loads ONNX, TensorFlow/TFLite, and NNEF models, op… | 97 | 3075 | active |
| Natively-AI-assistant/natively-cluely-ai-assistant Natively is a free, source-available desktop AI meeting assistant and interview copilot that provides real-time transcription, AI-generated… | 83 | 3036 | active |
| sahibzada-allahyar/YC-Killer A collection of open-source, enterprise-grade AI agents intended as free alternatives to commercial Y Combinator startups. It includes a de… | 60 | 2828 | active |
| iamsrikanthnani/pluely Pluely is a privacy-first desktop AI assistant that runs as an invisible always-on-top overlay, providing live meeting transcription, on-sc… | 82 | 2746 | active |
| Intent-Lab/VisionClaw VisionClaw is a real-time AI assistant app for Meta Ray-Ban smart glasses that streams camera frames and microphone audio to the Gemini Liv… | 59 | 2591 | active |
| VITA-MLLM/VITA VITA is an open-source interactive omni multimodal large language model (VITA-1.5) that supports real-time vision and speech interaction, s… | 26 | 2536 | active |
| apple/axlearn AXLearn is a Python deep learning library built on JAX and XLA for developing and training large-scale models, with an object-oriented conf… | 69 | 2375 | active |
| espressif/esp-adf Espressif's official Advanced Development Framework for building audio and multimedia applications on ESP32-series SoCs. It provides pipeli… | 77 | 2319 | active |
| floneum/kalosm Kalosm is a Rust ecosystem of crates providing simple interfaces for running pre-trained language, audio, and image models locally or remot… | 65 | 2227 | active |
| vitoplantamura/OnnxStream A lightweight C++ inference library for ONNX models that streams weights to run large models in very little memory, accelerated by XNNPACK.… | 56 | 2089 | active |
| ROCm/FastFlowLM FastFlowLM (FLM) is an NPU-first LLM inference runtime purpose-built and deeply optimized for AMD Ryzen AI NPUs (XDNA2), offering an Ollama… | 87 | 1967 | active |
| TuyaOpen TuyaOpen is an open-source, cross-platform C/C++ SDK and IoT OS for building AI-agent hardware on Tuya T-series MCUs, ESP32, Beken, LN882H,… | 86 | 1888 | active |
| software-mansion/react-native-executorch React Native ExecuTorch is a declarative React Native library for running AI models on-device, powered by Meta's ExecuTorch runtime. It shi… | 88 | 1750 | active |
| waybarrios/vllm-mlx vllm-mlx is a vLLM-style LLM inference server for Apple Silicon Macs built on native MLX, exposing both OpenAI and Anthropic compatible API… | 82 | 1618 | active |
| TOM88812/xiaozhi-android-client A Flutter-based cross-platform voice chat client for the xiaozhi AI assistant ecosystem, supporting real-time voice interaction and text co… | 65 | 1604 | active |
| semperai/amica Amica is an open-source web application for conversing with customizable 3D characters through voice chat, speech recognition, and vision. … | 61 | 1599 | active |
| dindin0497/SeeIt SeeIt is an inclusive Android app with two accessibility modes: one that converts spoken speech into text and plays corresponding ASL (Amer… | 38 | 1540 | active |
| sauravpanda/BrowserAI BrowserAI is a TypeScript library for running LLMs, speech recognition, text-to-speech, and audio separation models directly in the browser… | 73 | 1452 | active |
| ARahim3/mlx-tune A Python library for fine-tuning LLMs, vision-language, audio (TTS/STT), embedding, OCR, and JEPA models natively on Apple Silicon Macs usi… | 69 | 1416 | active |
| elevenyellow/handcrafted-persona-engine Persona Engine is a Windows desktop application that drives a Live2D avatar with an AI pipeline: microphone speech recognition, an LLM guid… | 67 | 1381 | active |
| morettt/my-neuro An open-source AI desktop companion framework inspired by Neuro-sama, letting users build a customizable Live2D character with sub-second v… | 81 | 1374 | active |
| espressif/esp-box ESP-BOX is Espressif's AIoT development framework for the ESP32-S3-BOX series of development boards, built on the ESP32-S3 Wi-Fi + Bluetoot… | 57 | 1321 | active |
| Capsize-Games/airunner AI Runner is a privacy-focused desktop application for running local AI models offline, combining an AI chat companion with voice conversat… | 92 | 1319 | active |
| kubeai-project/kubeai KubeAI is a Kubernetes operator for serving machine learning models in production, supporting LLMs via vLLM and Ollama, vector embeddings, … | 95 | 1284 | active |
| GML-MMGroup/GMTalker GMTalker is an interactive 3D digital human system rendered with Unreal Engine, integrating speech recognition, speech synthesis, natural l… | 42 | 1239 | active |
| uezo/ChatdollKit ChatdollKit is a Unity SDK that turns 3D character models into voice-enabled chatbots and virtual assistants. It integrates LLMs (ChatGPT, … | 84 | 1227 | active |
| nobodywho-ooo/nobodywho NobodyWho is an open-source (EUPL-1.2) on-device LLM inference engine written in Rust, built on llama.cpp, with SDKs for Kotlin, Swift, Pyt… | 83 | 1122 | active |
| HITsz-TMG/Uni-MoE Uni-MoE is a family of open-source Mixture-of-Experts (MoE) based omnimodal large language models that understand and generate across text,… | 65 | 1118 | active |
| susiai/susi_chat A chat interface for communicating with a locally hosted LLM (via llama.cpp) through a terminal console, a browser-based console, or a voic… | 57 | 1036 | active |
| microsoft/torchscale A PyTorch library from Microsoft implementing foundation Transformer architectures such as DeepNet, Magneto, RetNet, LongNet, BitNet, and X… | 32 | 3143 | maintenance |
| i-Code Microsoft's i-Code is a collection of research models and frameworks for integrative, composable multimodal AI spanning vision, language, a… | 10 | 1700 | maintenance |
| yakGPT/yakGPT YakGPT is a locally running, browser-based ChatGPT UI that connects directly to the OpenAI API with your own key. It adds hands-free voice … | 31 | 1580 | maintenance |
| ARM-software/ML-KWS-for-MCU TensorFlow models and training scripts for keyword spotting (wake-word detection) on Arm Cortex-M microcontrollers, accompanying the 'Hello… | 32 | 1258 | maintenance |
| Syan-Lin/CyberWaifu CyberWaifu is a Python chatbot application that combines LLMs (ChatGPT, Claude) with TTS (edge-tts, Azure) to create realistic conversation… | 30 | 1102 | maintenance |
| susiai/susi_device SUSI Device provides sources to install the SUSI AI assistant stack on a Raspberry Pi, combining microphone/speaker, a small display, a loc… | 32 | 1000 | maintenance |
| evilsocket/cake Cake is a multimodal AI inference server written in Rust that runs text, image, and voice models on a single device or shards them across a… | 56 | 3126 | experimental |
| C-Nedelcu/talk-to-chatgpt A Chrome and Edge browser extension that lets users talk to ChatGPT using speech recognition and hear responses via text-to-speech, with op… | 32 | 1929 | abandoned |
| YodaOS YodaOS is a Linux distribution built on OpenWrt for voice-enabled IoT devices, using JavaScript as its primary application language. It tar… | 32 | 1227 | abandoned |
← prev page 6 / 6