Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient.

eSpeak NG is described as 'The eSpeak NG is a compact open source software text-to-speech synthesizer for Linux, Windows, Android and other operating systems. It supports more than 100 languages and accents. It is based on the eSpeak engine created by Jonathan Duddington' and is a Text to Speech service. There are more than 25 alternatives to eSpeak NG for a variety of platforms, including Windows, Web-based, Linux, Mac and Android apps. The best eSpeak NG alternative is Kokoro, which is both free and Open Source. Other great apps like eSpeak NG are RHVoice, NaturalReader, eSpeak and SherpaTTS .
Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient.



Natural Reader is a professional text to speech program that converts any written text into spoken words. The paid versions of Natural Reader have many more features.



eSpeak is a compact open source software speech synthesizer for English and other languages, for Linux and Windows.


SherpaTTS is an Android Text-to-Speech engine based on Next-gen Kaldi using Piper or Coqui voices.


Transform text into speech with natural synthesis, offering smooth and fine-tuned audio export. Create high-quality voiceovers, download outputs for diverse applications, and experience excellent synthesis. Supports various languages and operates on multiple platforms.




We're excited to introduce Chatterbox, Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations.
AIVocal is your all-in-one AI assistant for voice tasks—perfect for AI podcasting, speech generation, vocal editing, and voice control. From transcribing meetings to creating high-quality audio content, AIVocal makes voice work smarter and faster.

NextUp.com develops Windows text to speech (TTS) software applications like TextAloud that let your computer talk with AT&T Natural Voices. TextAloud can also be in Microsoft Word as a plug-in.

Dia is a 1.6B parameter text to speech model created by Nari Labs. It was pushed to the Hub using the PytorchModelHubMixin integration.




Mimic is a powerful TTS tool. Mimic is low-latency and has a small resource footprint. Its range of high quality voices also set it apart from other open source text-to-speech projects.