131–140 of 164 posts
> "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?
It's impressive but it's a shame that it's 2026 and despite remarkably lifelike speech, so many models fall on common issues like heteronyms ("the couple had a row because they couldn't agree where to row their boat"), realistic number handling and so on.
It's impressive but it's a shame that it's 2026 and despite remarkably lifelike speech, so many models fall on common issues like heteronyms ("the couple had a row because they couldn't agree where to row their boat"), realistic number handling and so on.
Yeah most models are quite bad at it. The industry term for it is: homograph disambiguation.
Earlier quoted context omitted.
That doesn't really change what I said though. It isn't crazy to call it useless without some form of ALS either. Given that old school synthesis has been able to do it for like 20 years or so.
How does state of the art matter when talking about usefulness? Is old school synthesis useless?
Earlier quoted context omitted.
Firefox should integrate that in their Reader Mode (the default System Voices are often very un-listable). Would seems like an easy win, and it's a non-AI feature so not polarising.
Not sure about macOS or Windows, but on Linux Firefox uses speech-dispatcher, which is a server, and Firefox is the client. Speech-dispatcher then delegates the text to the correct TTS backend. It basically runs a shell command, either sending the text to a TTS HTTP server using curl, or piping it to the standard input of a TTS binary. Speech-dispatcher commonly uses espeak-ng, which sounds robotic but is reportedly…
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?
Earlier quoted context omitted.
Being able to voice clone with PocketTTS seems major, it doesn't look like there's any support for that with Kokoro.
Zero shot voice clones have never been very good. Fine tuned models hit natural speaker similarity and prosody in a way zero shot models can't emulate. If it were a big model and was trained on a diverse set of speakers and could remember how to replicate them all, then zero shot is a potentially bigger deal. But this is a tiny model. I'll try out the zero shot functionality of Pocket TTS and report back.
Question: does anyone recommend a TTS that automatically recognizes emotion from the text it self?
Chatterbox does something like that. For example, if the input is "so and so," he and the verb is not just "said", but "chuckled", or "whispered", or "said shakily", the output is modified accordingly, or if there's an indication that it's a woman speaking it may pitch up during the quotation. It also tries to guess emotive content from textual content, such if a passage reads angry it may try to make it sound angry.…
Earlier quoted context omitted.
How does state of the art matter when talking about usefulness? Is old school synthesis useless?
No? But is it not unreasonable to expect "state of the art" TTS to be able to do at least what old school synthesis is capable of doing? Being "state of the art" means being the highest level of development or achievement in a particular field, device, procedure, or technique at a specific point in time. I don't think it's therefore unreasonable to expect supposed "state of the art" text-to-speech synthesis to do far…
Non sequitur. Unless the 'art' in question is the 'art of adding features', usually this phrase is to describe the quality of a very specific development, these are often not even feature complete products.