Search Results for "voice"

A set of AI-enabled effects, generators, and analyzers for Audacity. These AI features run 100% locally on your PC, no internet connection is necessary. OpenVINO™ is used to run AI models on supported accelerators found on the user's system such as CPU, GPU, and NPU.

Meow Voice Changer is a lightweight, real-time voice modulation tool for Windows, purrrfect for streaming and voice chats. Inspired by Battlestar Galactica Cylon and Viper comms but capable of many more effects, it offers pitch, tempo, wobble, ring modulation, flanging, echo, EQ, and radio effects like distortion and static. Process microphone input with a customizable effect chain.

...Its more focused on the "satan voice" filter, while the larger default version has 16 different filters you can mix and match. (Source code is included within the html file itself.)

...Background noise gone, mains hum gone, levels evened out, and it tells you what it changed. It reports in numbers rather than adjectives: before and after figures for background level, loudness and peak. On a typical run it lifts the voice tens of decibels further above the background, removes 50 Hz mains hum and levels the file to a loudness target you set. Three strengths. Two of them are ordinary filtering and need nothing downloaded at all. Only the strongest uses a trained model, and that model is half a megabyte. The cleaned copy is written beside the file it came from. ...

Spleeter is the Deezer source separation library with pretrained models written in Python and using Tensorflow. It makes it easy to train music source separation models (assuming you have a dataset of isolated sources), and provides already trained state of the art models for performing various flavours of separation. 2 stems and 4 stems models have state of the art performances on the musdb dataset. Spleeter is also very fast as it can perform separation of audio files to 4 stems 100x...

A free and open sourced patch editor for the Yamaha FB01 sound module.

The purpose of HSVT is the collection and setup of OSS audio tools for the processing of speech and vocals. The end result will be something between jack-rack and ardour, with partial emulation or co-operation with hardware-rack voice processors.

Yet another human-readable plaintext music notation language. Somewhat similar to ABC and also Guido. Empty lines divide blocks of music, and every line is for one voice. Blocks can be repeated and merged to simplify structured composing.