TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Coqui TTS: a deep learning toolkit for Text-to-Speech

94 pointsby tim--almost 3 years ago

8 comments

userbinatoralmost 3 years ago
The TTS performance graph is interesting but it would be even better to add another dimension for comparing their resource consumption (code size, RAM, CPU usage&#x2F;speed). For example, if &quot;Windows Male&quot; is <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Microsoft_text-to-speech_voices" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Microsoft_text-to-speech_voice...</a> then it&#x27;s an offline-only synthesiser that is relatively small and fast, while the Google ones are probably massive neural models that are only available as a service. Yet their speech performance seems to be quite similar according to that chart.
sneheshtalmost 3 years ago
This is pretty cool, I tried this, takes around 5 secs to generate the audio for a couple of sentences with my old 1080Ti.<p>I&#x27;ve been using Google TTS for generating audio for my reading list, this would be good time to build a simple api+worker wrapper around this and integrate into my app.
评论 #32385380 未加载
boredumbalmost 3 years ago
Very Cool! If anyone is interested in what a coqui sounds like (<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=LZUOiZG84c0" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=LZUOiZG84c0</a>)<p>Anyone who has ever fallen asleep anywhere in Puerto Rico will probably be quite familiar.<p>I used Coqui TTS a few months ago to roll my own speech controlled desktop in an hour or so, very cool stuff.
评论 #32394686 未加载
TheWellKnownEIPalmost 3 years ago
Coincidentally I&#x27;ve just started playing around with Coqui TTS for training on my own experimental datasets. I was naive enough to think I could get it to run on Windows instead of Linux, I would suggest you save yourselves the time and start from Linux if you&#x27;re giving it a go!
评论 #32385391 未加载
michelbalmost 3 years ago
What is currently the best open source toolkit to do TTS with your own voice?
Mindless2112almost 3 years ago
Looks to be a continuation of Mozilla TTS[1]. I&#x27;m kinda surprised there&#x27;s no mention unless you go back in the git history[2].<p>[1] <a href="https:&#x2F;&#x2F;github.com&#x2F;mozilla&#x2F;TTS" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;mozilla&#x2F;TTS</a> [2] <a href="https:&#x2F;&#x2F;github.com&#x2F;coqui-ai&#x2F;TTS&#x2F;tree&#x2F;e9e07844b77a43fb0864354791fb4cf72ffded11" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;coqui-ai&#x2F;TTS&#x2F;tree&#x2F;e9e07844b77a43fb0864354...</a>
pwillia7almost 3 years ago
Has anyone done any vocoding&#x2F;deep fakes using this? Appreciate any articles&#x2F;tips you can share if so.
评论 #32385442 未加载
IceHegelalmost 3 years ago
How is this different from TorToiSe TTS?
评论 #32386053 未加载