espeak-ng
YourTTS
Our great sponsors
espeak-ng | YourTTS | |
---|---|---|
25 | 3 | |
2,858 | 824 | |
5.3% | - | |
7.2 | 1.6 | |
3 days ago | 12 months ago | |
C | Jupyter Notebook | |
GNU General Public License v3.0 only | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
espeak-ng
-
IAMA senior javascript dev, ask me anything
I'm skeptical about a senior JavaScript developer claiming to be bored. Nonetheless, let's see. How would you go about modifying [this](ng/blob/master/emscripten/espeakng_glue.idl) IDL file, this C++ glue code, and the relevant Make file to compile eSpeak NG to JavaScript with Emscripten with SSML support enabled?
-
Is there a good text to speech program for linux?
eSpeak NG supports running on Linux, BSD, Mac, Android, Windows, has been compiled to WASM with Emscripten. See also espeak and meSpeak.js.
-
Vietnamese Phonology
I may have a solution, BUT I'm at an airport right now, so... Perhaps tonight I can give you some ideas. There is a program I used to make a few presets for myself. https://github.com/espeak-ng/espeak-ng/blob/master/docs/languages.md
-
[P] Balacoon: Fastest neural text-to-speech on CPU
For this one, I used espeak (https://github.com/espeak-ng/espeak-ng) as a text processor. It is almost 17 years old software and is pretty lacking, unfortunately. On the other hand, it's super fast and supports tens of languages. Long story short, punctuation introduces phrase break with a pause of fixed length, and capitalization is ignored.
-
Balacoon: python package for text-to-speech
I didnt not release trainy parts to build voices. I am considering, but there is so many packages already (coqui, espnet, piper, nemo, fairseq to name a few) that i focused on usability for now. Support for new languages is a different question. Everyone wants to train fancy neural nets. But support for new language is about writing rules and having language expertise. I did it for English (https://github.com/balacoon/en_us_normalization/tree/c1019cf878aa6baf25d6fff719cf418cca5a3107/production/classify). Doing it for all the other languages would probably take me a lifetime. Other speech synthesis solutions use 17-years old espeak for this purpose (https://github.com/espeak-ng/espeak-ng/blob/master/docs/languages.md). I introduced the fallback to it in Balacoon too. But generally, it is outdated technology and I believe we should do better.
-
Is there a good audio-to-IPA phone app that doesn’t assume a particular language?
espeak-ng works by first converting text to IPA and then pronouncing that. But im not sure im aware of a way to input arbitrary IPA, and also the quality is probably too low for you.
-
I Created A Web Speech API NPM Package Called SpeechKit
There are espeak-ng https://github.com/espeak-ng/espeak-ng and pocketsphinx https://github.com/cmusphinx/pocketsphinx which can be used locally without making external requests.
-
Which languages have readily available IPA equivalents to learn from?
There are automatic tools to convert a written form of a language to IPA, I'm personally aware of espeak-ng, which supports* a lot of languages.
-
Ask HN: Are there any good open source Text-to-Speech tools?
I've had good luck with https://github.com/espeak-ng/espeak-ng (for very specific purposes, and I was willing to wrangle IPA)
-
Node.js Native Messaging host
Web Speech API does not provide a means to capture audio output of speechSynthesis.speak(new SpeechSynthesis.speak()). Using Native Messaging we start a local server, send input text or SSML to the local server with fetch(), pass the input data to local speech synthesis engine, in this case espeak-ng, get response back as WAV in the browser, which we parse to Float32Array and write to a MediaStreamTrackGenerator which we then output speakers and/or share with peers (https://github.com/guest271314/native-messaging-espeak-ng; https://github.com/espeak-ng/espeak-ng/tree/master/chromium_extension).
YourTTS
-
[D] What are the best ways to make and run a fast custom TTS?
YourTTS is available in Coqui TTS. It's fast and rather easy to use, but at the cost of quality. It does English, French and Portuguese in the same model.
-
How can i use better text to speech services in linux?
For "natural" output you need a trained model for your language and a software for WaveNNN. YourTTS and coqui.ai are the two best approach for realtime TTS
- Use deep fake tech to say stuff with your favorite characters
What are some alternatives?
RHVoice - a free and open source speech synthesizer for Russian and other languages
StarGANv2-VC - StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion
TTS - 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
voice_conversion
piper - A fast, local neural text to speech system
autovc - AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
scrcpy - Display and control your Android device
tt-vae-gan - Timbre transfer with variational autoencoding and cycle-consistent adversarial networks. Able to transfer the timbre of an audio source to that of another.
aeneas - aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)
jukebox - Code for the paper "Jukebox: A Generative Model for Music"
SAM - Software Automatic Mouth - Tiny Speech Synthesizer