I wonder if this could be adapted into an app that can run completely offline?
Pocket TTS: A high quality TTS that gives your CPU a voice
121–130 of 164 posts
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#122Earlier quoted context omitted.
What are the advantages of PocketTTS over Kokoro? It seems like Kokoro is the smaller model, also runs on CPU in real time, and is more open and fine tunable. More scripts and extensions, etc., whereas this is new and doesn't have any fine tuning code yet. I couldn't tell an audio quality difference.
Less licensing headache, it seems. Kokoro says its Apache licensed. But it has eSpeak-NG as a dependency, which is GPL, which brings into question whether or not Kokoro is actually GPL. PocketTTS doesn't have eSpeak-NG as a dependency so you don't need to worry about all that BS. Btw, I would love to hear from someone (who knows what they're talking about) to clear this up for me. Dealing with potential GPL contamina…
If it depends on espeak NG code, the complete product is 100% GPL. That said, if you are able to change the code to take off the espeak dependency then the rest would revert to non-GPL (or even if it's a build time option that you can disable like FFMPEG with --enable-gpl)
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#123I wonder if this could be adapted into an app that can run completely offline?
Try `uvx pocket-tts serve`
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#124> "You can also clone the voice from any audio sample by using our repo."
Ok, who knows where I can get those high-quality recordings of Majel Barrett' voice that she made before she died?
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#125This is impressive. I just tried some sample verses, sounds natural. But there seems to be a bug maybe? Just for fun, I had asked it to play the Real Slim Shady lyrics. It always seems to add 1 extra "please stand-up" in the chorus. Anyone see that?
Hello Gabriel from Kyutai here, maybe it's related to the way we chunk the text? Can you post an issue on github with the extact text and voice? I'll take a look.
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#126Just added it to my codex plugin that reads summary of what it finishes after each turn and I am spooked! runs well on my macbook, much better than Samantha! https://github.com/agentify-sh/speak/
[dead]
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#127voices sound great! i see sample rate can be adjusted, is there any way to adjust the actual speed of the voice?
[dead]
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#128How large is the model and is it possible to train it read other languages, not only English?
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#129How large is the model and is it possible to train it read other languages, not only English?
After pip install pocket-tts all dependencies are 7.4 GB. And it generates at 2x speed on CPu. Neat!
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#130Earlier quoted context omitted.
But it wouldn't be for those who "speak exclusively English", rather, for those who speak English. Not only that but it's also common to have system language set to English, even if one's language is different. There's about 1.5B English speakers in the planet.
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…
> Ask a German whether their system language is English. Ask a French person. I can go on.
I'm German but my system language is English
Because translations often suck, are incomplete or inconsistent