Open Source Windows Speech Recognition Software
Sort By:
Speech Recognition Software for Windows
View 40 business solutionsBrowse free open source Speech Recognition software and projects for Windows below. Use the toggles on the left to filter open source Speech Recognition software by OS, license, language, programming language, and project status.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
Already Paying for an RMM? Get 50% Off Splashtop AEMAutomated OS and third-party patching for Windows and macOS, CVE prioritization with AI patch summaries, and built-in remote control that also supports Linux. Qualifying organizations switching from another RMM get up to 50% off year one.
-
1
whisper.cpp
Port of OpenAI's Whisper model in C/C++
whisper.cpp is a lightweight, C/C++ reimplementation of OpenAI’s Whisper automatic speech recognition (ASR) model—designed for efficient, standalone transcription without external dependencies. The entire high-level implementation of the model is contained in whisper.h and whisper.cpp. The rest of the code is part of the ggml machine learning library. The command downloads the base.en model converted to custom ggml format and runs the inference on all .wav samples in the folder samples. whisper.cpp supports integer quantization of the Whisper ggml models. Quantized models require less memory and disk space and depending on the hardware can be processed more efficiently. -
2
CMU Sphinx
Speech Recognition Toolkit
Thank you for visiting! ----> Maintenance and improvement work has MOVED to https://cmusphinx.github.io/ Please go there for the most recent software and documentation. <---- CMUSphinx is a speaker-independent large vocabulary continuous speech recognizer released under BSD style license. It is also a collection of open source tools and resources that allows researchers and developers to build speech recognition systems. -
3
Whisper
Robust Speech Recognition via Large-Scale Weak Supervision
OpenAI Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification. A Transformer sequence-to-sequence model is trained on various speech processing tasks, including multilingual speech recognition, speech translation, spoken language identification, and voice activity detection. These tasks are jointly represented as a sequence of tokens to be predicted by the decoder, allowing a single model to replace many stages of a traditional speech-processing pipeline. The multitask training format uses a set of special tokens that serve as task specifiers or classification targets. -
4
Buster
Captcha solver extension for humans
Save time by asking Buster to solve captchas for you. Buster is a Firefox extension which helps you to solve difficult captchas by completing reCAPTCHA audio challenges using speech recognition. Challenges are solved by clicking on the extension button at the bottom of the reCAPTCHA widget. It is not guaranteed that challenges are always solved, the limitations of the technology need to be considered. The continued development of Buster is made possible thanks to the support of awesome backers. If you'd like to join them, please consider contributing with Patreon, PayPal or Bitcoin. The success rate of the extension can be improved by simulating user interactions with the help of a client app. Follow the instructions from the extension's options to download and install the client app on Windows, Linux and macOS, or get the app from this repository. -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
5
OpenVINO
OpenVINO™ Toolkit repository
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference. Boost deep learning performance in computer vision, automatic speech recognition, natural language processing and other common tasks. Use models trained with popular frameworks like TensorFlow, PyTorch and more. Reduce resource demands and efficiently deploy on a range of Intel® platforms from edge to cloud. This open-source version includes several components: namely Model Optimizer, OpenVINO™ Runtime, Post-Training Optimization Tool, as well as CPU, GPU, MYRIAD, multi device and heterogeneous plugins to accelerate deep learning inferencing on Intel® CPUs and Intel® Processor Graphics. It supports pre-trained models from the Open Model Zoo, along with 100+ open source and public models in popular formats such as TensorFlow, ONNX, PaddlePaddle, MXNet, Caffe, Kaldi. -
6
Google2SRT
Download, save and convert multiple subtitles from YouTube videos
Google2SRT allows you to download, save and convert multiple subtitles and translations from YouTube and Google Video to SubRip (.srt) format, which is recognized by most video players. You can download XML subtitles or simply type video's URL, Google2SRT will do the rest. -
7
Speech recognition research toolkit
-
8
Diffgram
Training data (data labeling, annotation, workflow) for all data types
From ingesting data to exploring it, annotating it, and managing workflows. Diffgram is a single application that will improve your data labeling and bring all aspects of training data under a single roof. Diffgram is world’s first truly open source training data platform that focuses on giving its users an unlimited experience. This is aimed to reduce your data labeling bills and increase your Training Data Quality. Training Data is the art of supervising machines through data. This includes the activities of annotation, which produces structured data; ready to be consumed by a machine learning model. Annotation is required because raw media is considered to be unstructured and not usable without it. That’s why training data is required for many modern machine learning use cases including computer vision, natural language processing and speech recognition. -
9
Scribe
Free, open-source, and offline speech-to-text & voice control app.
Scribe is a free and open-source desktop assistant that brings powerful speech-to-text and voice control capabilities directly to your PC. It allows you to dictate text into any application, create custom voice commands, launch programs, and automate your workflow with text replacements. Version 1.3.0 adds offline punctuation and capitalization: periods, commas, question marks and capital letters appear automatically as you dictate (Russian and English via neural models, basic rules for 30+ other languages). Designed with privacy as a top priority, Scribe works completely offline. Your voice data never leaves your computer. Powered by the Vosk engine, it supports multiple languages and provides high-quality recognition without an internet connection. Runs on Windows and Linux. Scribe is the perfect tool for anyone looking to boost productivity, improve accessibility, or simply interact with their computer in a new, hands-free way. Source: https://github.com/AIgrator/Scribe -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
10
annyang!
Speech recognition for your site
annyang is a tiny javascript library that lets your visitors control your site with voice commands. annyang supports multiple languages, has no dependencies, weighs just 2kb and is free to use. annyang understands commands with named variables, splats, and optional words. Use named variables for one word arguments in your command. Use splats to capture multi-word text at the end of your command (greedy). Use optional words or phrases to define a part of the command as optional. annyang plays nicely with all browsers, progressively enhancing browsers that support SpeechRecognition, while leaving users with older browsers unaffected. Grab the latest version of annyang.min.js, drop it in your html, and start adding commands. You can easily add a GUI for the user to interact with Speech Recognition using Speech KITT. Speech KITT is fully customizable and comes with many different themes, and instructions on how to create your own designs. -
11
WhisperJAV
A subtitle generator for Japanese Adult Videos.
A subtitle generator for Japanese Adult Videos. Transformer-based ASR architectures like Whisper suffer significant performance degradation when applied to the spontaneous and noisy domain of JAV. This degradation is driven by specific acoustic and temporal characteristics that defy the statistical distributions of standard training data. -
12
Lip Reading
Cross Audio-Visual Recognition using 3D Architectures
The input pipeline must be prepared by the users. This code is aimed to provide the implementation for Coupled 3D Convolutional Neural Networks for audio-visual matching. Lip-reading can be a specific application for this work. Audio-visual recognition (AVR) has been considered as a solution for speech recognition tasks when the audio is corrupted, as well as a visual recognition method used for speaker verification in multi-speaker scenarios. The approach of AVR systems is to leverage the extracted information from one modality to improve the recognition ability of the other modality by complementing the missing information. The essential problem is to find the correspondence between the audio and visual streams, which is the goal of this work. We proposed the utilization of a coupled 3D Convolutional Neural Network (CNN) architecture that can map both modalities into a representation space to evaluate the correspondence of audio-visual streams using the learned multimodal features. -
13
NVIDIA NeMo
Toolkit for conversational AI
NVIDIA NeMo, part of the NVIDIA AI platform, is a toolkit for building new state-of-the-art conversational AI models. NeMo has separate collections for Automatic Speech Recognition (ASR), Natural Language Processing (NLP), and Text-to-Speech (TTS) models. Each collection consists of prebuilt modules that include everything needed to train on your data. Every module can easily be customized, extended, and composed to create new conversational AI model architectures. Conversational AI architectures are typically large and require a lot of data and compute for training. NeMo uses PyTorch Lightning for easy and performant multi-GPU/multi-node mixed-precision training. Supported models: Jasper, QuartzNet, CitriNet, Conformer-CTC, Conformer-Transducer, Squeezeformer-CTC, Squeezeformer-Transducer, ContextNet, LSTM-Transducer (RNNT), LSTM-CTC. NGC collection of pre-trained speech processing models. -
14
Omnilingual ASR
Omnilingual ASR Open-Source Multilingual SpeechRecognition
Omnilingual-ASR is a research codebase exploring automatic speech recognition that generalizes across a very large number of languages using shared modeling and training recipes. It focuses on leveraging self-supervised audio pretraining and scalable fine-tuning so low-resource languages can benefit from high-resource data. The project provides data preparation pipelines, training scripts, decoding utilities, and evaluation tools so researchers can reproduce results and extend to new language sets. It emphasizes modularity: acoustic modeling, language modeling, tokenization, and decoding are separable pieces you can swap or ablate. The repo is aimed at pushing practical multilingual ASR—robust to accents, code-switching, and domain shifts—rather than language-by-language systems. For practitioners, it’s a starting point to study transfer, zero-shot behavior, and trade-offs between model size, compute cost, and coverage. -
15
Flow Teleprompter
A Windows first teleprompter with voice tracking and AI drafting.
Flow is an ultra-lightweight, high-performance teleprompter for Windows built with Rust and Tauri. Designed for creators, presenters, and educators, Flow delivers a smooth, distraction-free reading surface with minimal CPU and RAM usage. Key Features: - 5 Playback Modes: Offline Voice Tracking (via local Vosk models), Word Highlight, Line-by-Line, Arrow Guide, and Continuous Smooth Scrolling. - Script Library & Manager: Save, search, organize, and switch between multiple scripts locally with quick file imports (.txt, .docx, .pdf). - Section Navigator: Break long scripts into structured milestones with live reading completion tracking. - Invisible Overlay: Keep your script visible to you while remaining invisible during screen sharing and video calls. - Real-Time Web Collaboration: Let guests edit scripts live from their browser via WebRTC (PeerJS). - Local-First Privacy: 100% offline data security, 8-language localization, and multi-monitor support. -
16
VideoSrt
Windows-GUI
This is an open source Windows-GUI software tool that can recognize video speech and automatically generate subtitle SRT files. VideoSrtIt is written in Golanglanguage and developed based on lxn/walk Windows-GUI toolkit. Open source software tool that can recognize video speech and automatically generate subtitle SRT files. It is suitable for business scenarios that quickly and batch generate Chinese/English subtitles and text files for media (video/audio). Recognize video/audio speech to generate subtitle files (support Chinese-English translation, bilingual subtitles) Extract speech text from video/audio. Batch translation, filter processing/encoding SRT subtitle files. Using the Alibaba Cloud speech recognition interface, the accuracy is high, and the standard Mandarin/English recognition rate is over 95%. Video recognition does not need to upload the original video, which is convenient, fast and time-saving. -
17
Extreme- Inspired by Jarvis
Presenting the Extreme inspired by Iron Man JARVIS!
How many of us have secretly wanted to break into Tony Stark's mansion and steal away the JARVIS assistant? Because after all, who doesn't want an assistant that is Artificial Intelligent, but also super friendly? Well, now you won't have to, because we spent some time on our drawing boards, and created our own. Presenting to you, Multiverse Extreme. Now, you can also have an AI assistant that will be the best personal assistant, you could have ever found. Period. All you need to do is download the assistant app, and begin your journey with Extreme. Extreme is fully capable of understanding conversations in English and giving you everything you could expect from it. And we mean everything. Want to bounce a question off the internet? Just ask Extreme your question, and let it handle getting you the answer to "What is radiation?" like a boss. Keep Calm and Call Extreme. Please Note: "Extreme" is in no way associated or endorsed with the actual character. -
18
VoiceCommander 2.0 Multilingual Offline
2.0 Offline multilingual voice control for Windows. Fast, private
Release 2,0 : Full project website: https://voicecommander2multilingual.sourceforge.io/ Return any reviews or problem to : ducktheapp@gmail.com VoiceCommander Multilingual Offline is a local voice command system for Windows, focused on speed, privacy, and simplicity. It runs entirely on your PC with no cloud services, no external APIs, and no internet connection. All voice recognition and commands are processed locally, ensuring full control of your data. The software allows you to control your computer using voice commands in multiple languages, including launching applications, managing system functions, and interacting with Windows. Features: - 100% offline (no cloud, no data sharing) - Multilingual voice commands - Control apps, browser, and system - OCR + text-to-speech screen reading - Portable (no installation) - No registry changes NVIDIA GPU recommended (GTX 1060+). CPU mode supported (slower). For any other information please contact : Ducktheapp -
19
AURA
Type in any Windows app at the speed of speech.
Press and hold the hotkey, speak, and release — Aura instantly transcribes your speech and types the text right under your cursor in any Windows application. Runs 100% offline via local models (Whisper, NVIDIA Parakeet with CUDA GPU acceleration) or connects to cloud providers (Gemini, Groq, OpenAI, Hugging Face, Custom API). 100% Free & Open Source (AGPL-3.0) — no subscriptions, paywalls, telemetry, or advertisements. -
20
Voconly
Free, open-source, offline speech-to-text tool for Windows and MacOS.
**voconly is a free, open-source, local-first AI voice input assistant that runs entirely on your device.** It turns speech into text locally and uses AI to polish, translate, organize, and transform your words into usable content, letting you replace keyboard input with your voice in any application. No audio uploads. No cloud dependency. Your voice stays on your device. Unlike cloud-based voice input software, voconly keeps all audio data local—no uploads, no internet required, complete privacy. Powered by local AI, it combines real-time speech recognition with on-device LLM post-processing. Supports multiple ASR models (Qwen-ASR, SenseVoice, Whisper, Parakeet) and offers customizable refinement modes: auto-polishing, professional formatting, cross-language translation. Perfect for privacy-conscious users, developers, writers, and professionals handling sensitive content. If you need reliable Windows voice input without cloud dependency, voconly is your solution -
21
Polaris programing with voice in Eclipse
Polaris, programing with voice in Eclipse IDE
With Polaris you have the possibility of incorporating speech into programing. Through use of this plugin in Eclipse IDE you can see that not only is it possible to provide an environment for a programing with voice, but that programing with voice it is part of the natural evolution of programming tools. VOICE COMMANDS eclipse task eclipse search eclipse skip eclipse format eclipse new eclipse save eclipse rename eclipse cut eclipse copy eclipse paste eclipse all eclipse delete eclipse close eclipse get eclipse hash eclipse string Efforts are made on daily basic to increase the range of functionality that can be controlled with voice. PREREQUISITE Windows OS and Eclipse IDE. Headphones with microphone, not mandatory, but it will improve speech recognition. Port Number that is setted in Polaris Preference page must not be used by any other application. -
22
1.) Investigation with cosine transform, and anti transform algorithm, with some voice recognition code. 2.) Translator: Croatian, English. 3.) 2D to 3D picture algorithm (principle) and new 2Dto3D video conversion code with AviSynth video scripting
-
23
Responding Partner
Control your PC computer with voice commands
Responding Partner is a windows application that enables you free talking with your computer which equipped with spoken animation character. You will be surprised how smart responding partner robot is. It also enables voice commands and controls to your computer for small task like open media files, open and close program, shutdown and restart computer,open website, type in editor, text to speech,etc. You can extend the ability by installing new plugin which available at files tab. We will continuous to update new plugin and animation character. Engine inside: - Speech Recognition - Text to Speech Requirements - Microphone -
24
Voxal voice changer
Transform your voice in real-time voxal voice changer
Voxal Voice Changer is a program that allows you to modify your voice by applying various effects (e.g. pitch change, echo, etc.) in real-time. Effects can be added in any sequence and in any combination, allowing you to distort your voice beyond recognition. Take your audio to the next level! Our powerful Voice Changer software lets you morph your voice in real-time with stunning AI-powered quality. Whether you're looking to have fun, protect your privacy, or create engaging content, we have the perfect voice for you. Audio can be captured from various sources, pre-listening is available, and the most popular audio formats are supported. -
25
JAVT - Just Another Voice Transformer
Just Another Speech Recognition and Text to Speech software.
JAVT or Just Another Voice Transformer (formerly, it is called Just Another Video Transcriber) is a Speech Recognition software that also support text to Speech and simple media conversion. JAVT allows you to convert from video files to audio wav file using ffmpeg, and then transcribe the audio file to text using either Microsoft SAPI or CMU Sphinx. You can also open a text file and allow JAVT to read it out for you through text to speech conversion.
