Directory
Published directory entries matching your search.
Discover is a Discord overlay for Linux written in Python using GTK3. It can show who is currently talking on Discord or display text and images from a preconfigured channel. It is fully customisable and can be positioned anywhere on the screen. The project states support for X11 and wlroots-based environments and offers command-line controls for starting, hiding and voice actions.
Documentation for Hermes Agent, a self-improving AI agent built by Nous Research. It describes a learning loop that creates skills from experience, improves them during use and remembers across sessions. The docs cover installation, context files, the memory and skills systems, voice mode, and connecting external tool servers via MCP.
Drumhaus is a browser-based drum machine and beat sequencer with 8 voices and 16 steps. It supports chainable patterns with per-step velocity, flam, ratchet and accent, per-voice filters, pitch and decay, and a master effects bus with reverb, compressor, phaser and saturation. Beats can be exported to WAV and presets shared via link. It is free and requires no account.
Eapy Slide is a tool for creating professional Electronic Press Kits (EPKs) for music artists. Users upload music, images, and text to generate formatted, shareable EPKs to pitch to labels, sync agents, and A&R representatives.
This is a duplicated instance of the Edge TTS Text To Speech Hugging Face Space, created by VoiceCloning-be. It offers the same text-to-speech functionality as the original, allowing users to input text, select voices, adjust speech rate and pitch, and generate customized audio output. The space is currently running.
Elai.io is an AI-powered tool that creates videos with customizable digital presenters from text. It offers a library of avatars, 75+ languages and voices, prompt-based video generation, voice cloning and presentation-to-video conversion. An integration uploads rendered videos directly to Thinkific courses.
ElevenReader is a free text read-aloud application. It can read aloud PDFs, eBooks, Kindle content and web articles, provides access to over 200,000 audiobooks, and offers 1000+ natural-sounding voices in 90+ languages, supporting file upload and link input for reading.
EmotiVoice is an open-source text-to-speech engine that speaks English and Chinese with over 2000 voices. Its main feature is emotional synthesis across emotions such as happy, excited, sad and angry. It provides a web interface and a scripting interface for batch generation.
Endel is a mobile app that provides personalized soundscapes intended to help with focus, relaxation and sleep, backed by neuroscience. The app adapts sounds in real time using inputs such as time of day, weather, heart rate and location. It also offers versions for Apple Watch, Amazon Alexa, TV, desktop and streaming platforms.
Ensembles is a realtime musical performance arranger app built with Vala and GTK and powered by FluidSynth, focused on live performance rather than recording. It offers voices, a split or layered keyboard, DSP effects, auto accompaniment styles and sampling pads. The project is in early development and not ready for production.
EspNet is an end-to-end speech processing toolkit hosted on GitHub. It is open-source software designed for speech processing tasks, with repository documentation covering installation steps, quick start guidance, and details of supported processing tasks. Contributors can participate in its development via the GitHub platform.
This is the official applications extensions page for Lyrion Music Server. It lists available extensions that add functionality including controller support, voice control, music visualization, integration with other tools, and automated playlist creation.
Ezstems is a website that uses Spleeter, a tool that creates stems from any audio file. Users upload an audio file and the resulting stems download in seconds. Free use is subject to limits, with a stated cap of 20 uploads per day and a 20MB file size limit.
Fast inference engine for whisper in C++ using CTranslate2.
Telegram bot named File Convert that converts files into voice, video, photo and sticker messages, and vice versa. A GitHub repository at github.com/revolter/FileConvertBot is referenced. Telegram users can launch it directly.
The Flight Safety Foundation X account describes the organization as a voice of safety for the global aerospace and aviation community and encourages membership. The account is based in Alexandria, VA, joined in March 2009, and had 2,889 posts.
Fliki is an AI video and audio tool that turns text, scripts, and blog posts into videos using over 2,000 AI voices in 80+ languages. It also offers text to speech, voice cloning, AI avatars, video translation, and an AI ad generator.
結婚式スピーチ・弔辞・年賀状・退職挨拶・お礼状・お詫び文など、冠婚葬祭と日常の手紙・挨拶文をAIが作成します。シチュエーションを選んで項目を埋めるだけで、そのまま使える文面が完成。82種類のツールを登録不要・完全無料で今すぐ使えます。.
FreeTTS is a browser-based audio workspace for creating speech, transcribing recordings, isolating vocals, enhancing voices, and editing audio. It offers Device TTS, AI Local TTS, and AI Cloud voices with free monthly characters. Browser tools handle audio cutting, joining, compression, and conversion, and a free plan includes 5,000 characters per month.
FunASR is an open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation and speaker diarization pipelines, with OpenAI-compatible and MCP serving. An industrial toolkit described for offline, streaming and edge deployment, it also covers emotion and audio-event models and keyword spotting. It is released under an MIT license.
Fusuma is a tool for creating slides from Markdown or MDX. It offers a zero-config setup and a command-line interface for development, building, exporting as PDF, deploying to GitHub Pages, presenter mode, and live mode. It can record slide timelines and voice for practice and supports drawing fluorescent marker lines during a speech. Fusuma requires Node 12.x or later.
Gartic Phone is an online version of the Telephone Game in which players write sentences, draw the sentences they receive, and describe the resulting drawings before the results are shown. It offers anonymous and authenticated play, and players choose a character and a nickname. The source suggests inviting friends to a voice call while playing.
Port of OpenAI's Whisper model in C/C++. It can be executed locally.
Good Tape is an automated transcription tool for video and audio that supports more than 100 languages. It offers speaker labels, AI summaries and a recorder app for iOS and Android. Uploaded recordings are processed and stored on servers inside the EU and are not used to train any model.
