mimic3
espeak-ng
mimic3 | espeak-ng | |
---|---|---|
24 | 25 | |
972 | 2,888 | |
1.9% | 2.8% | |
0.0 | 7.2 | |
5 months ago | 4 days ago | |
Python | C | |
GNU Affero General Public License v3.0 | GNU General Public License v3.0 only |
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.
mimic3
-
ArXiv Papers as Audiobooks
I'd like to take advantage of high quality TTS models but I'd prefer it to be one I may host myself.
Haven't found the right way yet, I'm considering: https://github.com/MycroftAI/mimic3
-
Any recommendation for human like voice AI model for conversation AI?
Fast or good, choose one
Mozilla's TTS is a python package installable with pip and uses cpu or gpu resources to render a choice of voices, they mostly sound natural and this is the good. https://github.com/mozilla/TTS
Mycroft's mimic3 is the default voice renderer for the Mycroft project that runs on pi hardware and sounds ok-ish, that is the fast. https://github.com/MycroftAI/mimic3
There are many others but these are the two I use according to if it needs to run on limited hardware or if the cycles fall freely from the sky.
- I used mimic3 in a few projects. It's relatively lightweight for a neural tts and gives acceptable results
- Mimic 3 Privacy-Focused Neural Text-to-Speech
-
Serverless voice chat with Vicuna-13B
It took quite a bit of digging to find the repo link https://github.com/MycroftAI/mimic3#readme and it's AGPL-3 for those interested in such things
- AI text-to-speech for private, non-commercial use?
-
Ask HN: Cool and Useful Dockerized Apps?
Recently seeing this testing mailserver linked on HN: https://tweedegolf.nl/en/blog/86/introducing-mailcrab
I was reminded of another useful tool, mimic3 by MycroftAI that gives you very nice TTS: https://github.com/MycroftAI/mimic3
So I was wondering: what other useful apps have been containerized for easy setup and great usefulness?
Basically the point of this question is to let people share these, for the benefit of all.
-
Text to speech
You could also try the successor but they didn't get around implementing the harvard voice yet and we don't like any of the voices that come with it.
-
Google tts/ amazon polly alternative?
https://github.com/MycroftAI/mimic3 this? it can be easily hosted on docker as well
- [D] Best TTS for a GPT powered voice assistant
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).
What are some alternatives?
piper - A fast, local neural text to speech system
RHVoice - a free and open source speech synthesizer for Russian and other languages
TTS - 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
bark - 🔊 Text-Prompted Generative Audio Model
mimic-recording-studio - Mimic Recording Studio is a Docker-based application you can install to record voice samples, which can then be trained into a TTS voice with Mimic2
scrcpy - Display and control your Android device
tortoise-tts - A multi-voice TTS system trained with an emphasis on quality
aeneas - aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)
mimic3-voices - Voice models for Mimic 3 text to speech system
SAM - Software Automatic Mouth - Tiny Speech Synthesizer