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

Pocket TTS: A high quality TTS that gives your CPU a voice

kyutai.org

Post reply on HN
Print view View original

81–90 of 164 posts

Re: Pocket TTS: A high quality TTS that gives your CPU a voice

#81

Post by supriyo-biswas »

tarcon wrote: post #75
lukebechtel wrote: post #13

Nice! Just made it an MCP server so claude can tell me when it's done with something :) https://github.com/Marviel/speak_when_done

macOS already has some great intrinsic TTS capability as the OS seems to include a naturally sounding voice. I recently built a similar tool to just run the "say" command as a background process. Had to wrap it in a Deno server. It works, but with Tahoe it's difficult to consistently configure using that one natural voice, and not the subpar voices downloadable in the settings. The good voice seems to be hidden someh…

> The good voice seems to be hidden somehow.

How am I supposed to enable this?

Re: Pocket TTS: A high quality TTS that gives your CPU a voice

#82

Post by vvolhejn »

aidenn0 wrote: post #52

I'm sure I'm being stupid, but every voice except "alba" I recognize from Les Miserables; is there a character I'm forgetting?

Václav from Kyutai here. Yes the original naming scheme was from Les Miserables, glad you noticed! We just stuck to Alba because that's the real name of the voice actor that provided the voice sample to us (see https://huggingface.co/kyutai/tts-voices), the other ones are either from pre-existing datasets or given anonymously.

Re: Pocket TTS: A high quality TTS that gives your CPU a voice

#84

Post by Paul_S »

mgaudet wrote: post #31

Eep. So, on my M1 mac, did `uvx pocket-tts serve`. Plugged in > It was the best of times, it was the worst of times, it was the age of wisdom, it was the age of foolishness, it was the epoch of belief, it was the epoch of incredulity, it was the season of Light, it was the season of Darkness, it was the spring of hope, it was the winter of despair, we had everything before us, we had nothing before us, we were all go…

All the models I tried have similar problems. When trying to batch a whole audiobook, the only way is to run it, then run a model to transcribe and check you get the same text.

Re: Pocket TTS: A high quality TTS that gives your CPU a voice

#85

Post by vvolhejn »

mgaudet wrote: post #31

Eep. So, on my M1 mac, did `uvx pocket-tts serve`. Plugged in > It was the best of times, it was the worst of times, it was the age of wisdom, it was the age of foolishness, it was the epoch of belief, it was the epoch of incredulity, it was the season of Light, it was the season of Darkness, it was the spring of hope, it was the winter of despair, we had everything before us, we had nothing before us, we were all go…

Václav from Kyutai here. Thanks for the bug report! A workaround for now is to chunk the text into smaller parts where the model is more reliable. We already do some chunking in the Python package. There is also a more fancy way to do this chunking in a way that ensures that the stitched-together parts continue well (teacher-forcing), but we haven't implemented that yet.

Re: Pocket TTS: A high quality TTS that gives your CPU a voice

#86

Post by IshKebab »

Buttons840 wrote: post #23
singpolyma3 wrote: post #15

Love this. It says MIT license but then readme has a separate section on prohibited use that maybe adds restrictions to make it nonfree? Not sure the legal implications here.

Good question. If a license says "you may use this, you are prohibited from using this", and I use it, did I break the license?

I think if they took you to court for cloning someone's voice without permission they would probably lose because this conflict makes the terms unclear.

Re: Pocket TTS: A high quality TTS that gives your CPU a voice

#88

Post by phoronixrly »

numpad0 wrote: post #67
phoronixrly wrote: post #28

Earlier quoted context omitted.

Let's indeed limit the use case to the system language, let's say of a mobile phone. You pull up a map and start navigation. All the street names are in the local language, and no, transliterating the local names to the English alphabet does not make them understandable when spoken by TTS. And not to mention localised foreign names which then are completely mangled by transliterating them to English. You pull up a br…

If you don't speak the local language anyway, you can't decode pronounced spoken local language names anyway. Your speech sub-systems can't lock and sync to the audio track containing languages you don't speak. Let alone transliterate or pronounce. Multilingual doesn't mean language agnostic. We humans are always monolingual, just multi-language hot-swappable if trained. It's more like you can make;make install docke…

> If you don't speak the local language anyway, you can't decode pronounced spoken local language names anyway

This is plainly not true.

> Multilingual doesn't mean language agnostic. We humans are always monolingual, just multi-language hot-swappable if trained

This and the analogy make no sense to me. Mind you I am trilingual.

I also did not imply that the model itself needs to be multilingual. I implied that the software that uses the model to generate speech must be multilingual and support language change detection and switching mid-sentence.

Re: Pocket TTS: A high quality TTS that gives your CPU a voice

#89

Post by rowanG077 »

Paul_S wrote: post #87

The speed of improvement of tts models reminds me of early days of Stable Diffusion. Can't wait until I can generate audiobooks without infinite pain. If I was an investor I'd short Audible.

Wouldn't audible be perfectly positioned to take advantage of this. They have the perfect setup to integrate this into their offering.

Re: Pocket TTS: A high quality TTS that gives your CPU a voice

#90

Post by jiehong »

numpad0 wrote: post #80
koakuma-chan wrote: post #63

Earlier quoted context omitted.

You can speak one language, switch to another language for one word, and continue speaking in the previous language.

But that's my point. You'll stop, switch, speak, stop, switch, resume. You're not going to be "I was in 東京 yesterday" as a single continuous sentence. It'll have to be broken up to three separate sentences spoken back to back, even for humans.

>"I was in 東京 yesterday"

I think it's the wrong example, because this is actually very common if you're a Chinese speaker.

Actually, people tend to say the name of the cities in their own countries in their native language.

> I went to Nantes [0], to eat some kouign-amann [1].

As a French, both [0] and [1] will be spoken the French way on the fly in the sentence, while the other words are in English. Switching happens without any pause whatsoever (because there is really only one single way to pronounce those names in my mind, no thinking required).

Note that with Speech Recognition, it is fairly common to have models understanding language switches within a sentence like with Parakeet.

Post reply on HN