Search Results for "speak"
Sort By:
Showing 136 open source projects for "speak"
View related business solutions-
One Monitoring Tool for IT, OT and Cloud | Free TrialModern infrastructure spans data centers, cloud platforms and factory floors, and every blind spot between them is a risk. PRTG supports SNMP, WMI, SSH and other standard protocols to monitor IT, OT and hybrid environments through one customizable dashboard. Build the views your team needs, from network health to application performance, without switching tools. Try PRTG free for 30 days now.
-
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.
-
1
pyttsx3
Offline Text To Speech synthesis for python
...The library exposes a simple but flexible API for controlling voice selection, speaking rate, volume, and other synthesis parameters from Python code. It supports both a high-level speak convenience function and a lower-level engine object with event hooks, queuing, and saving output to audio files. The repository includes examples and documentation that show how to adjust properties dynamically, persist synthesized output, and integrate pyttsx3 into GUIs or background services. -
2
TURF
A modular geospatial engine written in JavaScript
...It includes traditional spatial operations, helper functions for creating GeoJSON data, and data classification and statistics tools. Turf can be added to your website as a client-side plugin, or you can run Turf server-side with Node.js. Modular, simple-to-understand JavaScript functions that speak GeoJSON. Turf is a collection of small modules, you only need to take what you want to use. Takes advantage of the newest algorithms and doesn't require you to send data to a server. TypeScript definitions are packaged with each module. No DefinitelyTyped packages required. Turf uses GeoJSON for all geographic data. Turf expects the data to be standard WGS84 longitude, latitude coordinates. ... -
3
JoyAI-VL-Interaction
An Open Real-time Video-Language Interaction System
JoyAI-VL-Interaction is an open real-time video-language interaction system built around an 8B-scale vision-first model. It is designed to watch a webcam or livestream continuously and decide whether to speak, stay silent, or delegate a harder task. Unlike turn-based assistants, it focuses on event-driven interaction where timing matters as much as answer quality. The repository releases the model, training recipe, time-aligned interaction data, and deployable system together. Its system includes inference, WebUI, ASR, TTS, and background-agent services running on vLLM-based infrastructure. ... -
4
HTML To Markdown for PHP
Convert HTML to Markdown with PHP
...You want to store new content in HTML format but edit it as Markdown. You want to convert HTML email to plain text email. You know a guy who's been converting HTML to Markdown for years, and now he can speak Elvish. You'd quite like to be able to speak Elvish. You just really like Markdown. By default, HTML To Markdown preserves HTML tags without Markdown equivalents, like span and div. To strip HTML tags that don't have a Markdown equivalent while preserving the content inside them, set strip_tags to true. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
5
TimescaleDB
An open-source time-series SQL database optimized for fast ingest
TimescaleDB is the open-source relational database for time-series and analytics. Build powerful data-intensive applications. Become instantly productive with full SQL. Rely on the same PostgreSQL you know, love, and trust. Hyperfunctions make time series easier. Achieve 10-100x faster queries than with vanilla PostgreSQL, InfluxDB, MongoDB. Write millions of data points per second per node. Horizontally scale to petabytes. Don’t worry about cardinality. Simplify your stack, ask more complex... -
6
Textream
Textream is a free macOS teleprompter app for streamers, interviewers
Textream is an open-source, free macOS teleprompter application designed for streamers, podcasters, presenters, and interviewers who want a smooth, distraction-free way to stay on script. It runs natively on macOS and leverages on-device speech recognition to highlight each word in real time as you speak, keeping your focus where it belongs — on delivery rather than memorization. The interface supports multiple modes of use, such as classic constant-scroll auto-scrolling, voice-activated scrolling that pauses when you’re silent, and direct word tracking that syncs the displayed script to your spoken pace. Textream also includes flexible display modes, from a sleek notch-anchored overlay on laptops to an invisible-to-the-audience floating window or fullscreen experience. -
7
Open-LLM-VTuber
Open source AI VTuber platform with voice chat and Live2D 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. ... -
8
Real-Time AI Voice Chat
Have a natural, spoken conversation with AI
...RealtimeTTS then synthesizes the answer and streams speech back to the browser. Dynamic silence detection improves turn taking, while interruption handling lets users speak over an ongoing response. Multiple speech engines, including Kokoro, Coqui, and Orpheus, can be selected. Docker Compose simplifies deployment, although the original maintainer now treats the project as community-driven rather than actively developed. -
9
OpenLess
AI-polished text appears at your cursor in any app
OpenLess is an open-source voice input application for macOS and Windows that turns spoken ideas into polished text at the current cursor position. Users press a global hotkey, speak naturally, and release the key to receive cleaned-up text inside apps such as ChatGPT, Claude, Cursor, Notion, email clients, or chat boxes. Unlike basic dictation tools, it is designed to restructure loose speech into more useful writing, especially AI prompts with clearer context and constraints. The app follows a local-first and open-source approach, while allowing users to bring their own cloud credentials for speech recognition and chat completion services. ... -
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.
-
10
OpenMAIC
Open Multi-Agent Interactive Classroom
...The platform generates multiple learning scenes rather than a single static output, including slides, quizzes, interactive simulations, and project-based activities, which makes it feel closer to a guided lesson than a simple content generator. It also supports whiteboard-style visual explanation and text-to-speech delivery, allowing agents to draw, explain formulas, and speak aloud during instruction. OpenMAIC is built for flexible deployment, with support for direct use through its web experience as well as integration with OpenClaw so classrooms can be generated from messaging platforms such as Slack, Telegram, and Feishu. -
11
Smile
Statistical machine intelligence and learning engine
...If we can train advanced machine learning models on a PC, why buy a cluster? Write applications quickly in Java, Scala, or any JVM languages. Data scientists and developers can speak the same language now! Smile provides hundreds advanced algorithms with clean interface. Scala API also offers high-level operators that make it easy to build machine learning apps. And you can use it interactively from the shell, embedded in Scala. The most complete machine learning engine. Smile covers every aspect of machine learning. -
12
ElatoAI
Realtime AI Voice Agents with SoTA Multimodal AI models on Arduino ESP
...The system integrates voice synthesis and recognition by connecting an ESP32 device through secure WebSockets to edge server functions written in Deno, allowing users to speak naturally with AI agents hosted through cloud APIs including OpenAI’s Realtime API, Gemini’s Live API, xAI’s Grok Voice Agent API, and others. It includes a web client (built with Next.js) for managing devices, controlling volume, and viewing conversation transcripts, while the hardware runs optimized firmware to deliver responses in near real time — even supporting >15-minute uninterrupted conversations. -
13
iroh
IPFS reimagined
Iroh takes IPFS beyond the theoretical, to offer developers efficient infrastructure that scales data distribution past 10M devices. We have been working on and around IPFS nearly since its inception, and are starting out on a new implementation because we have unfinished business with IPFS. We believe the best days of the protocol are ahead, but to get there we need to ship an order-of-magnitude improvement that unlocks new platforms and use cases. We're building iroh to see just how far we... -
14
TEN
Open-source framework for conversational voice AI agents
...It includes a full ecosystem, TEN Turn Detection, TEN Agent, and TMAN Designer, allowing developers to rapidly assemble human-like, responsive agents that can see, speak, hear, and interact. With support for languages like Python, C++, and Go, it offers flexible deployment on both edge and cloud environments. Using components like graph-based workflow design, drag-and-drop UI (via TMAN Designer), and reusable extensions such as real-time avatars, RAG (Retrieval-Augmented Generation), and image generation, TEN enables highly customizable, scalable agent development with minimal code. -
15
peco
Simplistic interactive filtering tool
peco (pronounced peh-koh) is based on a python tool, percol. percol was darn useful, but I wanted a tool that was a single binary, and forget about python. peco is written in Go, and therefore you can just grab the binary releases and drop it in your $PATH. peco can be a great tool to filter stuff like logs, process stats, find files, because unlike grep, you can type as you think and look through the current results. Demos speak more than a thousand words! Here's me looking for a process on my mac. You can page through your results, and you can keep changing the query. When you combine tools like zsh, peco, and ghq, you can make managing/moving around your huge dev area a piece of cake! Search results are filtered as you type. When you find that line that you want, press enter, and the resulting line is printed to stdout, which allows you to pipe it to other tools. ... -
16
Mockito
Most popular Mocking framework for unit tests written in Java
...In particular anyone using Kotlin (which demands using mockito-inline) and PowerMock (which exacerbates the problem even more) will want to add this to all of their test classes to avoid a large memory leak. Fancy getting world-wide visibility and building up an eternal fame of an OSS contributor? Use the latest version! Hack and experiment. Speak up at the mailing list. Mockito is a mocking framework that tastes really good. It lets you write beautiful tests with a clean & simple API. Mockito doesn’t give you hangover because the tests are very readable and they produce clean verification errors. -
17
OpenVoice
Instant voice cloning by MIT and MyShell. Audio foundation model
...It is designed not only to match the timbre of the reference voice, but also to give granular control over style parameters such as emotion, accent, rhythm, pauses, and intonation. The model supports cross-lingual and even zero-shot cross-lingual voice cloning, so a speaker recorded in one language can be made to speak naturally in others. Architecturally, OpenVoice separates “tone color” cloning from style control, which makes it easier to keep a consistent identity while flexibly changing prosody or language. The project provides open-weight models, inference code, and examples, making it suitable both for research and for building production voice experiences. ... -
18
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... -
19
Lucebox
Fast LLM speculative inference server for consumer hardware
...It focuses on custom kernels, speculative prefill, speculative decoding, and model-specific optimizations rather than a generic one-size-fits-all runtime. The project includes a native C++ HTTP server with an OpenAI-compatible API, making it usable with tools that already speak the Chat Completions format. It supports CUDA and ROCm workflows, with Docker images for NVIDIA and AMD GPU setups. The repository also includes harnesses for testing compatibility with clients such as Claude Code, Codex, OpenCode, Hermes, Pi, OpenClaw, and Open WebUI. It is most useful for developers and AI enthusiasts who want to run optimized local models with lower latency, faster token generation, and hardware-aware inference behavior. -
20
Open Source Social Network
Open Source Social Network (OSSN) is a social networking software
...For most Linux servers running Apache v2, making the parent directory writable is very simple. If you are not running Apache v2 or are using a different type of webserver, you'll need to read your system's documentation or speak to your server administrator before proceeding. -
21
Obot MCP Gateway
Hosting, Registry, Gateway, and Chat Client
...The platform is designed to work with a variety of workflows and clients, so MCP servers managed inside Obot can be used by automation/agent frameworks as well as popular chat clients that speak MCP. -
22
Leaf 3
The easiest way to create clean, simple but powerful web apps and APIs
...Builds on top of standard PHP with a flexible learning curve + ZERO config. A rich, incrementally adoptable ecosystem of modules to build powerful apps with. Want a Leaf core team member to speak at your next event? Invite us to create a memorable and engaging experience for your attendees. -
23
Bot Framework Web Chat
A highly-customizable web-based client for Azure Bot Services
...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 from your users with Azure Cognitive Services. Benefit from open source SDK and tools to build, test, and connect bots that interact naturally with users, wherever they are. Build secure, global, scalable solutions that integrate with your existing IT ecosystem. Create an AI experience that can extend your brand and keep you in control of your own data. -
24
Ring
Unofficial packages for Ring Doorbells, Cameras, Alarm System
...With Ring you can control your home from your smartphone, tablet or PC. Each Ring device includes a camera, speakers, and an integrated microphone so you can view, listen, and speak to anyone on your property from anywhere. Ring's customizable motion sensors allow you to focus on the most important areas of your home. You will receive instant warnings as soon as your Ring device detects movement, so you are always the first to know if someone has gotten too close to your property. Ring allows you to monitor every corner of your property. -
25
Fun Audio Chat
Large Audio Language Model built for natural interactions
Fun Audio Chat is an interactive voice-first conversational AI platform designed to let users engage in natural spoken dialogue with large language models in real time, turning speech into context-aware responses while maintaining a smooth back-and-forth experience. It combines speech recognition, audio processing, and AI generation so users can speak simply and receive spoken replies, enabling applications such as virtual assistants, voice bots, and hands-free chat interfaces. The system supports dynamic audio input and output, meaning it can handle different voices, tones, and conversational contexts without forcing users into typed interactions. With real-time streaming, it minimizes latency and delivers responses quickly, making it suitable for applications where responsiveness matters, such as interactive demos, accessibility tools, and conversational games.
