On 8/1/22 11:35, Daniel Ortiz wrote: > Hello everyone, > Does anyone know of any open source or public domain text to speech that > allows the speech to be used in videos or more without copyright > infringement? > From, Daniel Ortiz As Rich mentioned, espeak-ng (successor and fork of espeak), is FOSS, and you can encode in a FOSS audio format (flac, ogg, etc). Note that the audio produced can still infringe copyright if the original text is not "free". Although, there might be a legal carve out for assistive purposes (screen reader for blind, etc).
[ASIDE: There was some hoopla a while back about ebook readers incorporating text-to-speech that got the audio book people all up in arms]. Here are some options: https://en.wikipedia.org/wiki/ESpeak *Recommended* A free and open-source, cross-platform, compact, software speech synthesizer. https://en.wikipedia.org/wiki/MBROLA *Recommended* MBROLA is speech synthesis software as a worldwide collaborative project. The MBROLA software is not a complete speech synthesis system; the text must first be transformed into phoneme and prosodic information in MBROLA's format, and separate software (e.g. eSpeakNG) is necessary. Mbrola voices greatly improve the speech generated from espeak et al. https://www.cstr.ed.ac.uk/projects/festival/ The Festival Speech Synthesis System offers a general framework for building speech synthesis systems as well as including examples of various modules. https://freebsoft.org/speechd *Recommended* Speech Dispatcher project provides a high-level /device independent/ layer for access to speech synthesis through a simple, stable and well documented interface. Speechd can be easily configured to use espeak-ng and mbrolo (for example) to simplify usage. A variety of software (KDE kmouth, KDE's okular PDF reader, calibre ebook management, mumble VOIP) have built-in support for speechd. Here's a comparison list (in need of update but still informative): https://en.wikipedia.org/wiki/Comparison_of_speech_synthesizers -Ed