Search Results for "text based"

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec. Mimi processes 24 kHz audio, down to a 12.5 Hz representation with a bandwidth of 1.1 kbps, in a fully streaming manner (latency of 80ms, the frame size), yet performs better than existing, non-streaming, codecs like SpeechTokenizer (50 Hz, 4kbps), or SemantiCodec (50 Hz, 1.3kbps). Moshi models two streams of audio: one corresponds to Moshi, and...

Podcastfy is an open-source Python package that transforms multi-modal content (text, images) into engaging, multi-lingual audio conversations using GenAI. Input content includes websites, PDFs, youtube videos as well as images. Unlike UI-based tools focused primarily on note-taking or research synthesis (e.g. NotebookLM), Podcastfy focuses on the programmatic and bespoke generation of engaging, conversational transcripts and audio from a multitude of multi-modal sources enabling customization and scale.

.... - MIDI Sync Commands (Stop, Song Position Pointer (0), Start) to prepare your devices. - Accurate MIDI Clock signals based on the song's BPM, keeping your gear perfectly in sync.

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers. DeepSpeech is an open-source Speech-To-Text engine, using a model trained by machine learning techniques based on Baidu's Deep Speech research paper. Project DeepSpeech uses Google's TensorFlow to make the implementation easier. A pre-trained English model is available for use and can be downloaded following the instructions in the usage docs. ...

Canorus is a free cross-platform music score editor. It supports an unlimited number and length of staffs, polyphony, a MIDI playback of notes, chord markings, lyrics, import/export filters to formats like MIDI, MusicXML, ABC Music, MusiXTeX and LilyPond

...Unlike most taggers for GNU/Linux, it uses a spreadsheet-like layout so that all the tags you want to edit by hand are visible and easily editable. The usual tag editor features are supported like extracting tag information from filenames, renaming files based on their tags by using patterns and basic tag editing. Then there’re Functions, which can do things like replace text, trim it, do case conversions, etc. Actions can automate repetitive tasks. Doing web lookups using Amazon (including cover art), Discogs (does cover art too!), FreeDB and MusicBrainz is also supported. There’s quite a bit more, but I’ve reached my comma quota. ...

AarTon is an automated text-to-speech application. It allows user to enter text in a web-based front-end and render these texts via a multi-channel sound card.

kuechenstation is a text mode client for the xmms2 daemon. Unlike other text mode client's it's not command line based, but features all you would expect from a graphical client: scrolling title, playlist editor, medialib browser

Text-User-Interface base SHOUTCast tuner. tuxshout can run comfortablely under low-memory and fossil environment. Supported input device is not only keyboard but also mouse! So you can use like gui.

DJBorg turns your MP3 playlist into a personalized radio station, adding randomly-generated DJ banter between tracks. Song information (based on ID3 tags), news, weather, and headlines are announced via a text-to-speech engine.

Pymel stands for: Python MP3-player by Eelco Lempsink and is a fully Python based program to use with the mp3serverbox (http://www.mp3sb.org). It doesn't play mp3's itself (yet). It runs within a curses environment (text-based).