141–150 of 164 posts
Question: does anyone recommend a TTS that automatically recognizes emotion from the text it self?
Is there any TTS engine that doesn't need cloning and has some sort of parameters one can specify? Like what if I want to graft on TTS to an existing text chat system and give each person an unique, randomly generated voice? Or want to try to get something that's not quite human, like some sort of alien or monster?
Is there any TTS engine that doesn't need cloning and has some sort of parameters one can specify? Like what if I want to graft on TTS to an existing text chat system and give each person an unique, randomly generated voice? Or want to try to get something that's not quite human, like some sort of alien or monster?
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.
I also find Javert in particular seems to put in huge gaps and spaces... side effect of the voice?
Earlier quoted context omitted.
> The good voice seems to be hidden somehow. How am I supposed to enable this?
My mistake, seems like I was refering to the Siri voice, which seems to be the default. It sounds good. It is selectable and to my surprise - even configurable in speed, pitch and volume - in the OS Accessibility settings -> System Voice -> Click on the (i) symbol. (macOS Tahoe)
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.
An all-TTS audiobook offering is just about as appealing as an all-stable-diffusion picture gallery (that is, not at all).
It's just too flat/dead compared to a human reader.
Hopefully the browsers will improve their built in TTS soon. It's still pretty unusable unless you really need it.
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.
Perhaps I have been not talking to voice models that much or the chatgpt voice always felt weird and off because I was thinking it goes to a cloud server and everything but from Pocket TTS I discovered unmute.sh which is open source and I think is from the same company as Pocket TTS/can I think use Pocket TTS as well I saw some agentic models at 4B or similar which can punch above its weights or even some basic model…