Search Results for "speech"
Sort By:
Showing 58 open source projects for "speech"
View related business solutions-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
Kokoro
An inference library for Kokoro-82M
Kokoro is an open-weight text-to-speech model and inference library built around the lightweight Kokoro-82M model. It is designed to generate high-quality speech from text while staying fast, compact, and cost-efficient compared with larger TTS systems. The project is useful for developers who want deployable speech synthesis without depending on a closed platform. It can be installed as a Python package and used in applications, scripts, experiments, or production workflows. ... -
2
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. ... -
3
annyang!
Speech recognition for your site
...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. -
4
Operit AI
Powerful Android AI agent with tools, automation, and Linux shell
Operit is a full-featured AI assistant and agent platform designed specifically for Android devices, aiming to go far beyond traditional chat-based interfaces. It integrates deep system-level capabilities with a wide range of tools, allowing the AI to perform real tasks such as file management, automation, and system control directly on the device. A standout aspect of the project is its built-in Ubuntu 24 environment, which enables users to run Linux commands, scripts, and development tools... -
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
5
Gemma Translator
Code to run an on-device, fully offline voice translator
Gemma Translator is an on-device voice translation system built around Google's Gemma 4 model and LiteRT-LM. It records speech, transcribes it locally, translates the resulting text, and speaks the translation back to another user. The entire inference workflow can operate offline after the required models are installed. Its React interface is optimized for compact handheld and Raspberry Pi displays, including two-person conversational layouts. A Python backend coordinates speech recognition, text-to-speech, and communication with the local language model. ... -
6
Pot Desktop
A cross-platform software for text translation and recognition
Pot-Desktop is a cross-platform productivity tool aimed at helping users quickly translate, perform OCR (optical character recognition), and synthesize speech for selected text or images — all with minimal friction. It supports picking text via mouse selection (“highlight-and-translate”), clipboard listening, or screenshot-based OCR; this makes it ideal for reading webpages, documents, images — or any on-screen text — and instantly getting translations or text extraction. The tool supports external plugin extensions, which means its functionality can be expanded far beyond the built-in options: you can add translation engines, OCR backends, TTS engines, vocabulary export (e.g. for language learning), and more. ... -
7
Supertonic
Lightning-fast, on-device TTS, running natively via ONNX
Supertonic is a lightning-fast, on-device text-to-speech system built around ONNX Runtime for maximum speed and portability. It focuses on running entirely locally, eliminating the need for cloud APIs and providing low latency and strong privacy guarantees, even on constrained devices like Raspberry Pi boards and e-readers. The core model is highly compact at around 66 million parameters, yet benchmarks show it can generate speech up to 167× faster than real time on modern consumer hardware and significantly outpace popular cloud TTS APIs in throughput and real-time factor. ... -
8
Open-LLM-VTuber
Open source AI VTuber platform with voice chat and Live2D avatars
Open-LLM-VTuber is an open source platform designed to create AI-powered VTuber characters that can interact with users through voice and animated avatars. It enables hands-free conversations with large language models by combining speech recognition, language processing, and text-to-speech synthesis into a single system. Users can speak directly to the AI character, and the system can respond with a generated voice while animating a Live2D avatar to simulate a talking virtual personality. Open-LLM-VTuber is modular, allowing developers to swap or configure different language models, speech recognition engines, and voice synthesis systems depending on their needs. ... -
9
comfyui-mixlab-nodes
Workflow and speech recognition app
...The project also brings Real-time Design features like screen capture and floating video nodes, enabling creative pipelines that mix live screen content, generative models, and visual effects. For audio and speech, it provides nodes for SpeechRecognition and SpeechSynthesis, plus workflows that combine voice generation with real-time face swapping and other audio-visual effects. On the AI side, it integrates multiple LLM providers (cloud and local), supports OpenAI-compatible endpoints, Siliconflow models, and includes prompt-focused utilities for random prompt generation, Chinese prompts, clip interrogation. -
$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
Node.js Client For NLP Cloud
NLP Cloud serves high performance pre-trained or custom models
...NLP Cloud serves high-performance pre-trained or custom models for NER, sentiment analysis, classification, summarization, dialogue summarization, paraphrasing, intent classification, product description and ad generation, chatbot, grammar and spelling correction, keywords and keyphrases extraction, text generation, image generation, blog post generation, text generation, question answering, automatic speech recognition, machine translation, language detection, semantic search, semantic similarity, tokenization, POS tagging, embeddings, and dependency parsing. It is ready for production, and served through a REST API. You can either use the NLP Cloud pre-trained models, fine-tune your own models, or deploy your own models. -
11
FastRTC
The python library for real-time communication
...FastRTC also integrates nicely with UI frameworks (e.g. via a web demo using Gradio), so developers can rapidly prototype and deploy real-time streaming applications without deep knowledge of low-level WebRTC internals. Because voice-enabled AI agents often involve many moving parts (speech-to-text, text processing, text-to-speech, streaming, session/chat management), FastRTC helps by handling the streaming aspect, leaving the rest to be plugged in modularly. -
12
Koodo Reader
A modern ebook manager and reader with sync and backup
...Customize the source folder and synchronize among multiple devices using OneDrive, iCloud, Dropbox, etc. Single-column, two-column, or continuous scrolling layouts. Text-to-speech, translation, progress slider, touch screen support, batch import. Add bookmarks, notes, highlights to your books. Adjust font size, font family, line-spacing, paragraph spacing, background color, text color, margins, and brightness. Night mode and theme color. Text highlight, underline, boldness, italics and shadow. Adjust font size, font family, line-spacing, paragraph spacing, background color, text color, margins, and brightness. -
13
Deep Chat
Customizable AI chat component for websites with API support
...It is built as a framework-agnostic solution, meaning it can work across various frontend environments, with additional support provided for React through a dedicated wrapper. Deep Chat includes advanced interaction capabilities such as speech input and output, file handling, and multimedia communication, making it suitable for rich conversational experiences. Internally, it uses a structured architecture that manages input, message handling, and service communication, allowing developers to intercept and customize requests and responses. -
14
FAY
Framework for building AI-powered interactive digital humans and agent
...Fay supports various types of digital humans, including 2.5D and 3D avatars, and can be integrated with applications running on mobile devices, PCs, web platforms, and embedded systems. Its architecture allows developers to combine different AI components such as speech recognition, text-to-speech, and large language models to create conversational digital agents. Fay provides multiple interfaces for text, voice, and digital human control, enabling developers to build interactive assistants, virtual presenters, or automated service agents. It also supports custom knowledge bases and configurable behaviors so developers can tailor the personality and responses of the digital human. -
15
AIGCPanel
One-stop AI digital human system with video voice synthesis tools
...It supports one-click model deployment, making it accessible even to beginners who may not be familiar with complex AI environments. AIGCPanel also includes tools for synchronizing lip movements with generated speech, enabling more realistic digital avatar videos. Built using modern desktop technologies, it delivers a cross-platform experience while maintaining a graphical interface for monitoring tasks and logs. -
16
Qwen Audio Agent
A realtime voice runtime that keeps Agents talking
Qwen Audio Agent is a real-time voice runtime designed to keep an AI assistant conversationally present while it performs longer tasks. It supports full-duplex speech, natural interruption, and continuous multi-turn dialogue. Direct questions are answered immediately, while tool-intensive work can be delegated to a background coding agent without ending the voice session. Users can start several independent tasks, check progress, cancel work, and continue discussing returned results. The system can reuse an agent’s existing tools, MCP servers, skills, configuration, and authentication through ACP-based integrations. ... -
17
Agili Hacker Podcast
AI tool that turns Hacker News posts into daily podcast updates
...This creates a hands-free way to stay updated on tech, startups, and developer discussions without reading long threads. Hacker Podcast combines content aggregation, natural language processing, and text-to-speech to deliver clear and digestible updates. Users can listen through web interfaces or podcast platforms, while also accessing written summaries for deeper reading. Built with modern web technologies, the project focuses on automation, speed, and accessibility. It supports continuous updates, allowing listeners to receive fresh insights daily. ... -
18
PyGPT
Open source personal AI Assistant for Linux, Windows and Mac
...It allows you to talk in chat mode and in completion mode, as well as generate images using DALL-E 2. PyGPT also adds access to the Internet for GPT via Google Custom Search API and Wikipedia API and includes voice synthesis using Microsoft Azure Text-to-Speech API. Moreover, the application has implemented context memory support, context storage, history of contexts, which can be restored at any time and e.g. continue the conversation from point in history, and also has a convenient and intuitive system of presets that allows you to quickly and pleasantly create and manage your prompts. ... -
19
Bot Framework Web Chat
A highly-customizable web-based client for Azure Bot Services
This repository contains code for the Bot Framework Web Chat component. The Bot Framework Web Chat component is a highly-customizable web-based client for the Bot Framework V4 SDK. The Bot Framework SDK v4 enables developers to model conversation and build sophisticated bot applications. This repo is part of the Microsoft Bot Framework, a comprehensive framework for building enterprise-grade conversational AI experiences. Create a bot with the ability to speak, listen, understand, and learn... -
20
Recorder
HTML5 js recording mp3 wav ogg webm amr format
Supports microphone recording and real-time processing in most of the implemented getUserMediamobile and PC browsers, mainly including Chrome, Firefox, Safari, iOS 14.3+, Android WebView, Tencent Android X5 kernel (QQ, WeChat, Mini Program WebView) , uni-app (App, H5), and most Android phones updated after 2021 have their own browsers; do not support: UC-based kernel (typical Alipay), most of the old domestic mobile phones that have not been updated have their own browsers and any other form of browser (including PWA, WebClip, any App) on low-version iOS (11.0-14.2) except Safari inside page). Provides multiple plug-in function support. Rich audio visualization, variable speed and pitch processing, speech recognition, audio stream playback, etc.; with powerful real-time processing support, it can be used in various web applications: from simple recording to complex real-time voice Recognition (ASR), and even audio-related games, are handled with ease. -
21
eGuideDog project develops free software for the blind. Currently, we focus on WebSpeech, Ekho TTS and WebAnywhere.
-
22
KoboldCpp
Run GGUF models easily with a UI or API. One File. Zero Install.
KoboldCpp is an easy-to-use AI text-generation software for GGML and GGUF models, inspired by the original KoboldAI. It's a single self-contained distributable that builds off llama.cpp and adds many additional powerful features. -
23
Audio Satanifier 666
Easily apply cool gnarly voice filters to your audio files
Transform pure innocent audio files, speech, music, etc into unholy demonic abominations. Audio Satanifier 666 is a fun easy-to-use browser-based tool forged in the pits of hell, for voice actors, musicians, sound designers, for memes, for creative projects or anyone else who want to twist their sound into something absolutely diabolical! Layperson friendly - you'll be able to apply cool effects to your audio file even if you know nothing about audio engineering. -
24
Flow Teleprompter
A Windows first teleprompter with voice tracking and AI drafting.
Flow is an ultra-lightweight, high-performance desktop teleprompter built with Tauri and Rust. It is designed for creators & presenters who need a clean reading surface without sacrificing advanced features like native voice tracking via local Vosk models and app-wide voice commands. It features five playback styles (highlight, scroll, line, arrow, and voice tracking), local-first privacy, and a built-in script editor. Version 1.9.0 introduces WebRTC-powered real-time collaborative... -
25
Transcrib — десктопное Electron-приложение для перевода аудио и видео в текстовый формат. Программа работает на базе мощной модели Whisper от OpenAI и Node.js. «Из коробки» в дистрибутив уже вшиты две легкие модели — `tiny` и `base`. Остальные (`small`, `medium`, `large`) можно скачать и обновлять прямо внутри приложения по мере необходимости. Логика простая: чем сложнее модель, тем выше качество текста, но тем дольше идет обработка.
