Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Neutts-air – Open-source, on device TTS

github.com

Post reply on HN
Print view View original

21–30 of 30 posts

Re: Neutts-air – Open-source, on device TTS

#21

Post by diggan »

mlla wrote: post #19
miki123211 wrote: post #13

> Install espeak (required dependency) This means using this TTS in commercial project is very dicy due to GPL3.

If only English support is required eSpeak could be replaced with MisakiSwift, which is under Apache 2.0 https://github.com/mlalma/MisakiSwift

Unfortunately seems it's Mac/iPhone only. Any cross platform alternatives?

Re: Neutts-air – Open-source, on device TTS

#22

Post by mrklol »

Model says it’s only supporting English, seems like the demos on their page for other languages are using an older model as the quality is worse.

But the current one seems really good, tested it for quite a bit with multiple kind of inputs.

Re: Neutts-air – Open-source, on device TTS

#23

Post by MarsIronPI »

kristopolous wrote: post #11
nopelynopington wrote: post #2

If this lives up to the demo it's a huge development for anyone looking to do realistic tts without paying to use an API

there's quite a number of pretty low overhead models around that do that in realtime these days.

But how many of them support voice cloning?

(Genuine question; I haven't seen any other than this one.)

Re: Neutts-air – Open-source, on device TTS

#24

Post by ottah »

aitchnyu wrote: post #16

Tangential, how easy is it to verify watermark with a smartphone and how easy is it to erase the watermark?

Removing the watermark looks trivial https://github.com/neuphonic/neutts-air/blob/d9761a3d938b06c...

Watermarking is usually very fragile and generally relies on an adversary not knowing about it. I honestly don't know why anyone bothers with it.

Re: Neutts-air – Open-source, on device TTS

#25

Post by mewmix »

curioussquirrel wrote: post #5

Could we finally get a decent opensource TTS app for Android? This project is very cool.

https://github.com/mewmix/nabu

you could try out nabu and let me know, i am working on adding more tts models in the future. It features all the kokoro voices, style mixing to create your own blend from their voices, basic kitten tts support, audio book / screen reader, LLMs and more :)

Re: Neutts-air – Open-source, on device TTS

#27

Post by nickthegreek »

MarsIronPI wrote: post #23
kristopolous wrote: post #11

Earlier quoted context omitted.

there's quite a number of pretty low overhead models around that do that in realtime these days.

But how many of them support voice cloning? (Genuine question; I haven't seen any other than this one.)

microsoft’s vibe voice.

Re: Neutts-air – Open-source, on device TTS

#28

Post by MarsIronPI »

nickthegreek wrote: post #27
MarsIronPI wrote: post #23

Earlier quoted context omitted.

But how many of them support voice cloning? (Genuine question; I haven't seen any other than this one.)

microsoft’s vibe voice.

VibeVoice (according to the repo description) is currently unavailable due to "misuse". But my impression was that it required a significant (>8GB) amount of VRAM? Or that it wasn't suitable for on-device for devices with low specs.

Re: Neutts-air – Open-source, on device TTS

#29

Post by nickthegreek »

MarsIronPI wrote: post #28
nickthegreek wrote: post #27

Earlier quoted context omitted.

microsoft’s vibe voice.

VibeVoice (according to the repo description) is currently unavailable due to "misuse". But my impression was that it required a significant (>8GB) amount of VRAM? Or that it wasn't suitable for on-device for devices with low specs.

its unavailable from their repo, but was released with an open license and mirrors exist. I'm not sure what the VRAM req are.

Re: Neutts-air – Open-source, on device TTS

#30

Post by MarsIronPI »

nickthegreek wrote: post #29
MarsIronPI wrote: post #28

Earlier quoted context omitted.

VibeVoice (according to the repo description) is currently unavailable due to "misuse". But my impression was that it required a significant (>8GB) amount of VRAM? Or that it wasn't suitable for on-device for devices with low specs.

its unavailable from their repo, but was released with an open license and mirrors exist. I'm not sure what the VRAM req are.

According to this issue[0] the 1.5B model needs 6GB of VRAM. Meanwhile it looks like NeuTTS is designed to be able to run on CPU, which is nice for older/lower-spec hardware.

0: https://github.com/microsoft/VibeVoice/issues/26#issuecommen...

Post reply on HN