domain: speech-processing
552 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| facebookresearch/denoiser A PyTorch library implementing a causal, real-time speech enhancement model that operates on raw waveforms to remove background noise and r… | 10 | 1899 | maintenance |
| Kyubyong/tacotron A heavily documented TensorFlow implementation of Tacotron, a fully end-to-end text-to-speech synthesis model. It includes training, prepro… | 32 | 1832 | maintenance |
| kalliope-project/kalliope Kalliope is a modular, always-on voice-controlled personal assistant framework written in Python, designed to run on Linux systems includin… | 23 | 1772 | maintenance |
| strob/gentle Gentle is a robust yet lenient forced aligner built on Kaldi that aligns audio speech with a known text transcript. It can be used as a Mac… | 65 | 1705 | maintenance |
| kan-bayashi/ParallelWaveGAN Unofficial PyTorch implementations of non-autoregressive neural vocoders including Parallel WaveGAN, MelGAN, Multi-band MelGAN, HiFi-GAN, a… | 23 | 1645 | maintenance |
| Delta-ML/delta DELTA is a deep learning based end-to-end natural language and speech processing platform built on TensorFlow and Python 3. It provides one… | 10 | 1607 | maintenance |
| vanshg/MacAssistant MacAssistant is a macOS application that integrates the Google Assistant into the Mac menu bar using the Google Assistant SDK. It is writte… | 23 | 1603 | maintenance |
| google/uis-rnn A Python library implementing the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm for segmenting and clustering se… | 10 | 1588 | maintenance |
| Marak/say.js A Node.js library that provides text-to-speech by shelling out to platform-native TTS engines (macOS `say`, Windows SAPI, Linux Festival). … | 32 | 1531 | maintenance |
| beyondcode/writeout.ai A self-hosted Laravel web application that transcribes uploaded audio files using OpenAI's Whisper API and translates the transcripts via t… | 71 | 1525 | maintenance |
| syl22-00/pocketsphinx.js PocketSphinx.js is a speech recognition library that runs entirely in the web browser, built by compiling the PocketSphinx C recognizer to … | 32 | 1508 | maintenance |
| google/live-transcribe-speech-engine Android client libraries from Google's Live Transcribe app for streaming real-time speech recognition via the Google Cloud Speech API. It p… | 10 | 1499 | maintenance |
| s-macke/SAM SAM (Software Automatic Mouth) is a tiny text-to-speech synthesizer written in C, adapted from the 1982 Commodore 64 speech software. It in… | 32 | 1497 | maintenance |
| wit-ai/pywit pywit is the official Python SDK for Wit.ai, Facebook's natural language processing platform. It provides a Wit client class for extracting… | 67 | 1485 | maintenance |
| YuanGongND/ast Official PyTorch implementation of the Audio Spectrogram Transformer (AST) from the Interspeech 2021 paper, which applies a Vision Transfor… | 32 | 1472 | maintenance |
| microsoft/SpeechT5 Microsoft's unified-modal speech-text pre-training framework implementing SpeechT5 and related models (SpeechLM, SpeechUT, VALL-E X, WavLLM… | 32 | 1449 | maintenance |
| m1guelpf/yt-whisper A Python CLI tool that downloads YouTube videos with yt-dlp and generates subtitle files (VTT) using OpenAI's Whisper speech recognition mo… | 32 | 1446 | maintenance |
| cmusphinx/sphinx4 Sphinx-4 is a speaker-independent, continuous speech recognition library written entirely in Java, originating from CMU and industry resear… | 32 | 1437 | maintenance |
| hungtraan/FacebookBot A Facebook Messenger chatbot ('Optimist Prime') that supports voice recognition, natural language processing, and contextual follow-up conv… | 32 | 1424 | maintenance |
| DragonComputer/Dragonfire Dragonfire is an open-source virtual assistant for Ubuntu-based Linux distributions, combining speech recognition, text-to-speech, and NLP … | 23 | 1407 | maintenance |
| innnky/emotional-vits Emotional VITS is a voice synthesis (TTS) model based on VITS that enables emotion-controllable speech generation without requiring manual … | 32 | 1392 | maintenance |
| LuckyHookin/edge-TTS-record A Windows desktop tool that records Microsoft Edge's online neural text-to-speech voices (e.g., Xiaoxiao, Yunyang) and saves the output as … | 23 | 1370 | maintenance |
| Jackywine/Bella Bella is a self-hosted Node.js web application that acts as a personalized AI digital companion with voice interaction. It combines Whisper… | 48 | 6379 | experimental |
| kripken/speak.js speak.js is a port of the eSpeak C++ speech synthesizer to JavaScript via Emscripten, enabling text-to-speech in the browser using only Jav… | 32 | 1335 | maintenance |
| CSTR-Edinburgh/merlin Merlin is a toolkit from the University of Edinburgh's CSTR for building deep neural network models for statistical parametric speech synth… | 23 | 1321 | maintenance |
| facebookresearch/svoice SVoice is a PyTorch implementation of the ICML paper 'Voice Separation with an Unknown Number of Multiple Speakers' from Facebook AI Resear… | 10 | 1315 | maintenance |
| Renovamen/Speech-Emotion-Recognition A Python library implementing speech emotion recognition with Keras/TensorFlow 2 using LSTM, CNN, SVM, and MLP models. It extracts audio fe… | 32 | 1314 | maintenance |
| kakaobrain/pororo PORORO is a Python library from Kakao Brain that provides unified access to dozens of pretrained neural models for natural language process… | 10 | 1305 | maintenance |
| elanmart/cbp-translate A demo application that live-translates foreign-language speech in videos into subtitles, mimicking the Cyberpunk 2077 translation effect. … | 32 | 1274 | maintenance |
| sdkcarlos/artyom.js Artyom.js is a JavaScript library that wraps the Web Speech APIs (webkitSpeechRecognition and speechSynthesis) to add voice control, speech… | 23 | 1269 | maintenance |
| mravanelli/SincNet SincNet is a PyTorch neural architecture that processes raw audio waveforms using parametrized sinc band-pass filters in the first convolut… | 32 | 1243 | maintenance |
| pollen-robotics/dtw A small Python module implementing Dynamic Time Warping (DTW), a similarity measure between temporal sequences. It offers a basic pure-Pyth… | 23 | 1230 | maintenance |
| PlayVoice/vits_chinese A Chinese text-to-speech library combining VITS with BERT-based prosody embeddings and NaturalSpeech infer-loss features, supporting ONNX c… | 23 | 1227 | maintenance |
| Alexander-H-Liu/End-to-end-ASR-Pytorch A PyTorch implementation of end-to-end automatic speech recognition (ASR), formerly known as Listen, Attend and Spell. It supports seq2seq … | 32 | 1208 | maintenance |
| 2fps/recorder A JavaScript library for recording audio in the browser using the HTML5 Web Audio API. It supports recording, pausing, resuming, playback, … | 23 | 1206 | maintenance |
| clovaai/voxceleb_trainer A PyTorch framework for training and evaluating speaker recognition and verification models on the VoxCeleb datasets. It implements multipl… | 67 | 1175 | maintenance |
| YaoFANGUK/video-subtitle-generator A Python application with both GUI and CLI interfaces that generates subtitle files (SRT) from video or audio using local Whisper-based spe… | 32 | 1175 | maintenance |
| bawangxx/XZVoice XZVoice is a free, open-source desktop text-to-speech application built with Electron, Vue, and ElementUI. It uses Alibaba Cloud's speech s… | 23 | 1168 | maintenance |
| spring-media/TransformerTTS A TensorFlow 2 implementation of a non-autoregressive Transformer-based neural network for text-to-speech synthesis, based on FastSpeech an… | 10 | 1161 | maintenance |
| Kyubyong/dc_tts A TensorFlow implementation of DC-TTS, a text-to-speech model based on deep convolutional networks with guided attention. It includes train… | 32 | 1156 | maintenance |
| openinterpreter/01 An open-source voice interface platform that lets users control computers conversationally, powered by Open Interpreter. It pairs a Python … | 16 | 5156 | experimental |
| synesthesiam/opentts OpenTTS is a text-to-speech server that unifies access to multiple open source TTS systems (Larynx, Glow-Speak, Coqui-TTS, MaryTTS, flite, … | 10 | 1118 | maintenance |
| synesthesiam/voice2json voice2json is a collection of command-line tools for offline speech-to-text and intent recognition on Linux, supporting 18 languages via en… | 10 | 1105 | maintenance |
| auspicious3000/autovc AUTOVC is a PyTorch implementation of a many-to-many non-parallel voice conversion framework that performs zero-shot voice style transfer u… | 32 | 1100 | maintenance |
| alumae/kaldi-gstreamer-server A real-time full-duplex speech recognition server built on the Kaldi toolkit and GStreamer framework, implemented in Python. It streams aud… | 32 | 1093 | maintenance |
| Edresson/YourTTS YourTTS is a zero-shot multi-speaker text-to-speech and voice conversion model built on VITS, implemented in the Coqui TTS framework. It su… | 23 | 1053 | maintenance |
| aliutkus/speechmetrics A Python library that wraps several objective speech quality metrics (MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR) behind a unified API. It su… | 32 | 1051 | maintenance |
| pykaldi/pykaldi PyKaldi is a Python scripting layer providing wrappers for the C++ APIs of the Kaldi speech recognition toolkit and OpenFst library. It ena… | 47 | 1039 | maintenance |
| descriptinc/melgan-neurips Official PyTorch implementation of MelGAN, a GAN-based non-autoregressive vocoder that inverts mel-spectrograms into raw audio waveforms fo… | 32 | 1039 | maintenance |
| ggeop/Python-ai-assistant Jarvis is a Python voice-controlled AI assistant for Linux that recognizes speech, responds conversationally, and executes commands like op… | 23 | 1014 | maintenance |
| NATSpeech/NATSpeech A PyTorch framework for non-autoregressive text-to-speech (NAR-TTS), containing official implementations of PortaSpeech (NeurIPS 2021) and … | 23 | 1004 | maintenance |
| enhuiz/vall-e An unofficial PyTorch implementation of the VALL-E text-to-speech audio language model, built on the EnCodec tokenizer. It provides trainin… | 31 | 2976 | experimental |
| Priler/jarvis JARVIS is an offline, privacy-respecting voice assistant built in Rust with Tauri, using neural networks for speech-to-text, text-to-speech… | 53 | 2909 | experimental |
| fikrikarim/parlor Parlor is a fully on-device, real-time multimodal voice assistant similar to GPT-Live, combining speech recognition, a Gemma vision-languag… | 78 | 2039 | experimental |
| Mini-Omni Mini-Omni is an open-source multimodal large language model that performs real-time end-to-end speech-to-speech conversation with streaming… | 22 | 1922 | experimental |
| Standard-Intelligence/hertz-dev Hertz-dev is an open-source 8.5B parameter autoregressive base model for full-duplex conversational audio, released by Standard Intelligenc… | 22 | 1799 | experimental |
| antirez/voxtral.c A pure C, zero-dependency inference implementation of Mistral's Voxtral Realtime 4B speech-to-text model, with a streaming C API and CLI fo… | 45 | 1738 | experimental |
| collabora/WhisperFusion WhisperFusion is a real-time voice chat application that combines WhisperLive speech-to-text, a Mistral/Phi LLM, and WhisperSpeech text-to-… | 26 | 1647 | experimental |
| lucidrains/naturalspeech2-pytorch A PyTorch implementation of NaturalSpeech 2, a zero-shot text-to-speech and singing synthesizer that combines a neural audio codec with a l… | 20 | 1333 | experimental |
| linyiLYi/voice-assistant A simple single-script Python demo of a local voice assistant that uses Whisper (via Apple MLX) for speech recognition and a local Yi large… | 26 | 1323 | experimental |
| CSCB/vibe-mouse An open-source Python desktop application that redefines mouse interaction by letting users bind customizable 'Skills' to buttons, with mul… | 55 | 1086 | experimental |
| openai/openai-realtime-api-beta A Node.js and browser reference client library for OpenAI's Realtime API, enabling real-time voice and text conversations with GPT models. … | 22 | 1016 | experimental |
| susiai/susi_shell A suite of Python-based command line tools for interacting with AI services directly from the terminal, including chat, text completion, tr… | 41 | 1002 | experimental |
| mozilla/DeepSpeech DeepSpeech is an open-source, offline speech-to-text engine based on Baidu's Deep Speech research paper and implemented with TensorFlow. It… | 10 | 26771 | abandoned |
| supertone-inc/supertonic Supertonic is a lightning-fast, on-device multilingual text-to-speech system powered by ONNX Runtime, with a compact 99M-parameter open-wei… | 58 | 13734 | abandoned |
| voicepaw/so-vits-svc-fork A fork of so-vits-svc providing singing voice conversion with realtime support and an improved interface, built on PyTorch and PyTorch Ligh… | 82 | 9327 | abandoned |
| MycroftAI/mycroft-core Mycroft Core is the core software of the Mycroft open-source voice assistant platform, providing wake-word listening, speech recognition, n… | 10 | 6611 | abandoned |
| unCaptcha unCaptcha2 is a Python-based security research tool that defeats Google's ReCaptcha v2 audio challenges by submitting the audio to free spe… | 32 | 4917 | abandoned |
| agermanidis/autosub Autosub is a Python command-line utility that auto-generates subtitles for video or audio files. It performs voice activity detection, tran… | 32 | 4191 | abandoned |
| buriburisuri/speech-to-text-wavenet A TensorFlow implementation of end-to-end English speech recognition based on DeepMind's WaveNet architecture, trained with CTC loss on sen… | 32 | 4002 | abandoned |
| innnky/so-vits-svc A singing voice conversion (SVC) framework that uses a SoftVC content encoder with VITS to transform one singer's voice into another timbre… | 10 | 3779 | abandoned |
| Kitt-AI/snowboy Snowboy is a C++-based hotword (wake word) detection library by KITT.AI with bindings for Python, Android, and other platforms, enabling al… | 23 | 3364 | abandoned |
| zzw922cn/Automatic_Speech_Recognition An end-to-end automatic speech recognition system implemented in TensorFlow, supporting Mandarin and English with models like DeepSpeech2, … | 32 | 2831 | abandoned |
| coqui-ai/STT Coqui STT is an open-source deep learning toolkit for training and deploying speech-to-text models, built on TensorFlow with bindings for m… | 23 | 2606 | abandoned |
| react-native-voice/voice A React Native speech-to-text library providing voice recognition on iOS and Android with both online and offline support. The package is n… | 10 | 2162 | abandoned |
| joshnewlan/say_what A Python script that listens to conference call audio via speech-to-text (IBM Watson) and alerts the user on HipChat when their name is men… | 32 | 2087 | abandoned |
| wzpan/dingdang-robot Dingdang is an open-source Chinese voice conversation robot / smart speaker project that runs on Raspberry Pi. It uses pluggable STT/TTS en… | 10 | 1873 | abandoned |
| tomlepaine/fast-wavenet A Python/TensorFlow library implementing an efficient O(L) generation algorithm for Wavenet-style autoregressive models using dynamic progr… | 32 | 1772 | abandoned |
| justLV/onju-voice A hackable AI home assistant platform that replaces the internals of a Google Nest Mini with a custom ESP32-S3 PCB, paired with a server th… | 63 | 1711 | abandoned |
| Ayanaminn/N46Whisper A Google Colab notebook application that generates Japanese subtitle files from video using the faster-whisper speech recognition model. It… | 36 | 1708 | abandoned |
| NVIDIA/OpenSeq2Seq OpenSeq2Seq is a TensorFlow-based toolkit for building and training sequence-to-sequence models for neural machine translation, speech reco… | 10 | 1558 | abandoned |
| elevenlabs/elevenlabs-mcp The official ElevenLabs Model Context Protocol (MCP) server, exposing ElevenLabs text-to-speech, speech-to-text, voice design, and conversa… | 10 | 1532 | abandoned |
| fossasia/susi_smart_box SUSI.AI Smart Box is an open-source smart speaker / voice assistant hardware project built around the SUSI.AI assistant. It provides the so… | 10 | 1529 | abandoned |
| sc0ty/subsync A C++ tool that automatically synchronizes subtitle files with movie or TV audio using speech recognition. It detects spoken audio in the v… | 10 | 1423 | abandoned |
| zenorocha/voice-elements A pair of Polymer-based Web Components (<voice-player> and <voice-recognition>) that wrap the Web Speech API for speech synthesis (text to … | 23 | 1348 | abandoned |
| dingdang-robot/dingdang-robot Dingdang is an open-source Chinese voice conversation robot / smart speaker project that runs on Raspberry Pi and other Linux hosts. It use… | 10 | 1330 | abandoned |
| MycroftAI/mimic3 Mimic 3 is a fast, local neural text-to-speech engine developed by Mycroft for the Mark II voice assistant, usable as a Python library, CLI… | 29 | 1264 | abandoned |
| alexa/avs-device-sdk The Alexa Voice Service (AVS) Device SDK is a C++ SDK for commercial device makers to integrate Alexa voice assistant capabilities directly… | 10 | 1252 | abandoned |
| rhasspy/wyoming-satellite A Python application that turns a Raspberry Pi (or similar Linux device) with a microphone and speaker into a remote voice satellite using … | 10 | 1244 | abandoned |
| xiph/LPCNet LPCNet is a low-complexity C implementation of the WaveRNN-based LPCNet neural vocoder for efficient speech synthesis and compression. It a… | 32 | 1221 | abandoned |
| maum-ai/voicefilter An unofficial PyTorch implementation of Google AI's VoiceFilter system, which isolates a target speaker's voice from noisy mixed audio give… | 32 | 1216 | abandoned |
| basveeling/wavenet A Keras implementation of DeepMind's WaveNet, a generative neural network model for raw audio synthesis. It supports training on datasets l… | 32 | 1052 | abandoned |
| BrasD99/HeyGenClone An open-source Python application that clones the HeyGen video translation system, translating videos into multiple languages with voice ov… | 10 | 1027 | abandoned |
| huggingface/transformers Hugging Face Transformers is a Python library that serves as the model-definition framework for state-of-the-art machine learning models ac… | 95 | 164475 | stable |
| Unsloth Unsloth is a desktop application for running and fine-tuning LLMs, diffusion, embedding, and audio models locally, with support for NVIDIA,… | 94 | 74883 | active |
| mudler/LocalAI LocalAI is an open-source, self-hosted AI inference runtime that runs LLMs, vision, speech, image, and video models behind OpenAI/Anthropic… | 93 | 48696 | active |
| huggingface/candle Candle is a minimalist machine learning framework for Rust focused on performance and ease of use, with CPU and CUDA GPU support. It ships … | 73 | 20955 | active |
| xszyou/Fay 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 | 13455 | active |
| RunanywhereAI/runanywhere-sdks RunAnywhere is a set of cross-platform SDKs (Swift, Kotlin, React Native, Flutter, TypeScript, C++) over a shared C++ core for running AI m… | 85 | 10282 | active |
| xorbitsai/inference Xinference is an open-source model serving platform for deploying LLMs, embedding, speech, image, and multimodal models via a unified OpenA… | 91 | 9523 | active |