uncloseai.
Welcome to uncloseai.com - Free LLM & Text To Speech Artificial Intelligence Service
Introducing uncloseai & Hermes & Qwen & TTS Speech Endpoints
At uncloseai., we offer free AI services powered by multiple AI models and a TTS (Text-to-Speech) endpoint. Our mission is to provide accessible AI tools for everyone, embodying the principles of both free as in beer & free as in freedom. You can interact with our models without any cost, and you are encouraged to contribute and build upon the open-source code & models that we use.
Available Endpoints:
- hermes.ai.unturf.com/v1 - General purpose conversational AI
- qwen.ai.unturf.com/v1 - Specialized coding model
- speech.ai.unturf.com/v1 - Text-to-speech
See our Model Discovery docs to query the current model IDs being hosted.
We intend to be a drop in replacement, you can use the existing open source OpenAI client to communicate with us.
uncloseai.js - Client-Side AI for Everyone
This page includes the uncloseai.js script which adds a floating "uncloseai." button in the bottom right corner. Click it to interact with Hermes AI directly from your browser.
This is a web client-only solution - no server required. Add AI capabilities to any static site or CDN with just one line of code.
✨ One-Line Installation
<script src="https://uncloseai.com/uncloseai.js" type="module"></script>📖 Read the full uncloseai.js documentation →
Code Examples
We provide comprehensive code examples for using the uncloseai. API with popular programming languages. Each example demonstrates both streaming and non-streaming modes with Hermes (general purpose AI) and Qwen 3 Coder (specialized coding model).
Quick Start Examples:
- Python Examples - Complete examples using the OpenAI Python client library
- Node.js Examples - Complete examples using the OpenAI Node.js client library
42 Programming Languages:
We provide SDK implementations with streaming support for 42 programming languages! Browse all language examples:
🔗 Browse All 42 Language Examples →
Includes: AWK, Bash, C, C++, C#, Clojure, COBOL, Common Lisp, Crystal, D, Dart, Deno, Elixir, Erlang, F#, Fortran, Go, Groovy, Haskell, Java, JavaScript, Julia, Kotlin, Lua, Mojo*, Nim, OCaml, Odin, Perl, PHP, PowerShell, Prolog, Python, R, Ruby, Rust, Scala, Scheme, Tcl, V, VB.NET, and Zig!
* Mojo implementation is non-streaming only (Lightbug HTTP library doesn't yet support SSE streaming as of 2025-10-15)
uncloseai. book - Machine Learning Reference Guide:
📚 Purchase the uncloseai. book on unturf.com Shop →
Comprehensive reference guide covering inference clients, streaming implementations, and best practices for all 42 programming languages.
All examples use the OpenAI-compatible API interface, making it easy to integrate with existing code. Simply change the base_url to point to our endpoints. See our Model Discovery docs for endpoint URLs and how to query current model IDs.
How we run inference
Want to contribute idle GPU time or reproduce everything in your own cluster?
📖 Read the full inference setup documentation →
Open Source & Public Domain
uncloseai. is completely public domain - free as in beer, free as in freedom. AI for all, internet for all, open web for everyone.
📦 Source Code: https://git.unturf.com/engineering/unturf/uncloseai.com
📄 Full Documentation: See README.rst in the repository for complete technical details, architecture, and contribution guidelines.