# Text To Speech in Julia

**URL:** https://discourse.julialang.org/t/text-to-speech-in-julia/104189
**Category:** New to Julia
**Tags:** text-to-speech, tts
**Created:** [September 24, 2023, 3:40am UTC](https://discourse.julialang.org/t/text-to-speech-in-julia/104189 "2023-09-24T03:40:16Z")
**Posts on this page:** 1
**Showing post:** 5

<div class="post-metadata">

### Author: ![Palli](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/palli/32/3380_2.png) [@Palli](https://discourse.julialang.org/u/Palli)
#### Post date: [February 27, 2025, 10:28am UTC](https://discourse.julialang.org/t/text-to-speech-in-julia/104189/5 "2025-02-27T10:28:37Z")

</div>

Which one do you like to be wrapped? Which is best? There’s no clear answer to that… and it depends on e.g. the language supported.

[https://www.datacamp.com/blog/best-open-source-text-to-speech-tts-engines](https://www.datacamp.com/blog/best-open-source-text-to-speech-tts-engines)

Best might be nr. 2 there, GPL3-licenced (nr. 1 is Java-based):

> **[GitHub - espeak-ng/espeak-ng: eSpeak NG is an open source speech synthesizer...](https://github.com/espeak-ng/espeak-ng)**
>
> eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.

> **[Best free text-to-speech software of 2025](https://www.techradar.com/news/the-best-free-text-to-speech-software)**
>
> Make it easier to listen to what you've type

> When selecting the best free text-to-speech software is best for you depends on a range of factors (not to mention personal preference). … We also want to test the accessibility features of these tools to see how they work for every kind of user out there. We have highlighted, for instance, whether certain software offer dyslexic-friendly fonts, such as the number two on our list, Natural Reader.

AI/deep learning based are going to be best like this one (but you could also argue a, smaller, package that accesses platform-provided TTS, that will likely improve over time, but will not be consistent across platforms):

> **[Text-to-speech • Hume AI](https://www.hume.ai/text-to-speech)**
>
> A text-to-speech system that understands what it's saying

> OCTAVE TTS, the first text-to-speech system built on LLM intelligence. Unlike conventional TTS […]  
> Hume’s state-of-the-art expression measurement models for the voice, face, and language are built on 10+ years of research and advances in semantic space theory pioneered by Alan Cowen.

> **[Free Text to Speech & AI Voice Generator | ElevenLabs](https://elevenlabs.io)**
>
> Create the most realistic speech with our AI audio tools in 1000s of voices and 32 languages. Easy to use API's and SDK's. Scalable, secure, and customizable voice solutions tailored for enterprise needs. Pioneering research in Text to Speech and AI...

> **[Free Text-To-Speech for 28+ languages & MP3 Download | ttsMP3.com](https://ttsmp3.com/)**
>
> Easily convert text to natural US English voice and 50+ languages/accents for free. Listen online or download as MP3.

I confirmed that last one even supports Icelandic (but it’s not perfect, as expected, maybe for most other languages).

TTS is available in platforms like Windows and Android, but will be inferior for a while (also likely free software), but going forward it will be a perfect standard feature to be expected, like font rendering now, so then for sure relying on it will be better than bundling TTS in a package, or calling a web API.

There’s no need to do it in Julia from scratch, probably worse (reuse good stuff out there):

> [@Can Julia make voice synthesizer using pressure simulation?](https://discourse.julialang.org/t/can-julia-make-voice-synthesizer-using-pressure-simulation/106220):
>
> A good synthetic speaker could talk, sing, and perform lots of stuffs. So, the question today is… would it be possible for Julia to synthesize voice by simulating vibration or even aIr pressure? (Maybe it’s totally just me wanting to create a synthetic singer with Julia.)

I couldn’t confirm TTS (yet) available for Julia (easily, without Python involvment, though pretty easy with PythonCall.jl), but doing the reverse problem is already available, without involving Python:

> **[GitHub - aviks/Whisper.jl: Implementation of OpenAI Whisper model based on...](https://github.com/aviks/Whisper.jl)**
>
> Implementation of OpenAI Whisper model based on whisper.cpp

[Whisper was state-of-the-art, then updated, but is no longer; new SOTA as of last week or so (from China if I recall), this is till a very active research area, more so than TTS, but TTS is also moving along.]

A lot is available already:

> **[GitHub - svilupp/awesome-generative-ai-meets-julia-language: Comprehensive guide to generative AI projects and...](https://github.com/svilupp/awesome-generative-ai-meets-julia-language)**
>
> Comprehensive guide to generative AI projects and resources in Julia.

> **[GitHub - redashu/awesome-Artificial-And-Machine-Learning-Stuff: A curated list of awesome Machine Learning...](https://github.com/redashu/awesome-Artificial-And-Machine-Learning-Stuff)**
>
> A curated list of awesome Machine Learning frameworks, libraries and software.

> **[JustSayIt.jl](https://juliapackages.com/p/justsayit)**
>
> Software and high-level API for offline, low latency and secure translation of human speech to computer commands or text on Linux, MacOS and Windows

> **[SPTK.jl](https://juliapackages.com/p/sptk)**
>
> A thin Julia wrapper for Speech Signal Processing Toolkit (SPTK) API

> **[ProToPortal.jl](https://juliapackages.com/p/protoportal)**
>
> ProToPortal: The Portal to the Magic of PromptingTools and Julia-first LLM Coding

I did find some false positives while looking into this:

> **[TrillionDollarWords.jl – patalt](https://www.patalt.org/blog/posts/trillion-dollar-words/)**
>
> A short post introducing a small new Julia package that facilitates working with the Trillion Dollar Words dataset and model published in a recent ACL 2023 paper.

> **[TrillionDollarWords.jl](https://juliapackages.com/p/trilliondollarwords)**
>
> A small Julia package to facilitate working with the Trillion Dollar Words dataset.

---

_[View the full topic](https://discourse.julialang.org/t/text-to-speech-in-julia/104189)._