speech synthesis Archives

Kokoro – Open-Weight Text-to-Speech Model

Kokoro is a lightweight open-weight text-to-speech model offering local speech synthesis, multiple languages, voices, and speed control.

MeloTTS is a multilingual text-to-speech library written in Python for generating natural-sounding speech locally.

Dia is a text to speech model capable of generating ultra-realistic dialogue in a single pass.

RHVoice is a multilingual speech synthesizer. The aim is to give visually impaired people access to a synthesis voice with a screen reader.

Gespeaker is a GTK-based frontend for eSpeak. Like eSpeak, Gespeaker is free and open source software.

eSpeak NG (Next Generation) is a continuation of the eSpeak with more feedback from native speakers. It supports more than 100 languages and accents.

Coqui TTS (TTS) is a library for advanced Text-to-Speech generation. It offers pretrained models in more than 1,100 different languages.

Tortoise TTS is a multi-voice text-to-speech system trained with an emphasis on quality.