Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.
Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
Start Free
$300 Free Credits to Build on Google Cloud
New customers can spin up VMs, build with AI, and query data at no cost.
Put 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.
InproTK is an Incremental Spoken Dialogue Processing Toolkit, that is, a toolkit to help you build dialogue systems that listen and talk incrementally, allowing for advanced interactional behaviour.
Please see our Wiki for more information: http://sourceforge.net/p/inprotk/wiki/
Speect is a multilingual TTS system. It offers a full text-to-speech system with various API's, as well as an environment for research and development of TTS systems and voices.
It is written in ANSI C and uses a plug-in mechanism for extensions. Speect also includes an extensive set of Python bindings for quick implementation of new ideas, these bindings are derived from SWIG interface files and can easily be extended for other languages supported by SWIG.
Speect is free and open...
Serves music files, playlists, HTML files, etc using http/WebDAV. Music files are categorized using metainformation (e.g. id3 tags) and this metainformation is stored in a MySQL database for sorting and searching operations.
Birdsim is a python application which goal is to simulate bird calls in 3d environment. Birdsim's main use-case is to create an ambient, natural sound-scape in homes and offices. Try it in a cold rainy day and feel the force of nature !
A sequencer specialized for extended just intonation tuning systems. Rationale does not use scales, only collections of notes related by frequency ratio, infinitely transposable. Any rational frequency ratio can be an interval, but no tempered tunings.
a contributory, location-aware media platform for us all
This is Roundware V1. For V2, please see GitHub repository: https://github.com/hburgund/roundware-server
Roundware is a client/server pair for creating participatory location-sensitive audio experiences. It was initially developed for the sound art installation ROUND, by Halsey Burgund, exhibited at the Aldrich Contemporary Art Museum.
Development for version 2 has been handled privately for a variety of reasons, but will be released soon! Please contact us if you need code sooner.
ASR-Builder provides an easy-to-use interface to the HTK toolkit, that allows users to build ASR systems. ASR-Builder provides a platform that performs house-keeping tasks when using HTK and also provides default training/testing/recognition scripts.
Command line application (and eventually GUI) for removing specific tags from ID3 v1 and v2 headers.
Built on top of id3lib, so future id3 revisions will always be supported.
Aldrin is an open source modular music sequencer/tracker for the GNU/Linuxoperating system. Aldrin is currently in beta stage and fully functional. Feel free to try and use it.
Open-source content and evaluation framework for music transcription systems. Can be used as monophonic or polyphonic database, through software mixing.
DirectPython is a C++ extension to the Python programming language which provides access to DirectX (9.0c) API, including Direct3D, DirectSound, DirectShow and DirectInput.
Remote control your PC (Win, Linux, Mac) via Bluetooth with a Symbian phone running PyS60. Uses plugins for different apps and supports other remote control systems. Plugins: WinAMP, MediaPlayerClassic, WindowsMediaPlayer, MouseControl, VLC, XMMS-alike
The goal of the CarOS project is to design and implement the software and hardware systems necessary to provide a mobile computing platform in a vehicle. The CarOS will be Linux based.
This software provides a web GUI for configuring and operating a streaming mp3 server, and also provides feedback on the streams status. The software is written in Python and is distributed under a GPL licence.
PSPy is a content manager for the Sony PSP. You will have acces to your homebrews, games backup, savegames, videos and music. Written in Python for Unix systems, using Glade/pyGTK, under the GPL license.
AFX is an X11-based, extensible, graphical, and highly configurable frontend primarily for use on tv-connected systems. The original design goal is a joystick-controlled frontend for an entertainment (games, emulators, audio, and video) box.
NovaX is a set of programs that is being devloped for small company's and beginners in the fields of HTML and programming. Coded in Python and C++, this is also a good replacement for MS Office. NOTE: This requires Python to be on your PC. ( Python.org )
A full-featured, GTK-based control panel for IceWM, featuring an IceWM theme designer, IceSoundManager (sound events), IcePref2, & tools to manage wallpaper, cursors, keys, window options, & more. IceWMCP has a familiar, Control Panel-like interface.
Pymprovisator is a program for jazz musicians. Jazz music is based on improvisation and this program is intended to help musicians to improvise. The user sets the song parameters and the program generates a MIDI file with an adequate accompaniment.
Open Source Application for databasing your Music Collection(s). iChoons will utilize other open source products such as MySQL, Apache Webserver and PHP as well as Python / wxPython and SQL Lite. We will also be including tools written in Python for Win3
Songer is an ID3 tagger designed for the ROX desktop that supports the drag-and-drop nature of ROX. It is designed to be a simple tagging utility. Songer currently only supports MP3s and ID3 version 1 tags. Future support of ID3v2 and OGG files is planne