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.
Neutts-air – Open-source, on device TTS
11–20 of 30 posts
Re: Neutts-air – Open-source, on device TTS
#12Every couple of weeks I see a new TTS model showcased here and it’s always difficult to see how they differ from one another. Why don’t they describe the architecture and details of the trailing data? My cynical side thinks people just take the state-of-the-art open source model, use an LLM to alter the source, minimal fine tuning to change the weights and they are able to claim “we built our own state of the art tts…
Without the resources to do a study to see if the quality is actually better or worse than other options, these open-TTS models must be judged by what you think of their output. (That is, do your own study.)
I've found some of them to be surprisingly good. I keep a list of them, as I have future project ideas that might need a good one, and each has its own merits.
I'm yet to find one that does good spoken informal Chinese. I'd appreciate if anyone can suggest one!
Re: Neutts-air – Open-source, on device TTS
#13> Install espeak (required dependency)
This means using this TTS in commercial project is very dicy due to GPL3.
Re: Neutts-air – Open-source, on device TTS
#14Every couple of weeks I see a new TTS model showcased here and it’s always difficult to see how they differ from one another. Why don’t they describe the architecture and details of the trailing data? My cynical side thinks people just take the state-of-the-art open source model, use an LLM to alter the source, minimal fine tuning to change the weights and they are able to claim “we built our own state of the art tts…
The special sauce here is that it is built on a very small LLM (Qwen) which means this can run on CPU-only, or even on micro devices like Raspberry Pi or a mobile phone.
Architecturally it's similar to other LLM-based TTS models (like OuteTTS) but the underlying LLM makes them able to release it under an Apache 2 license.
Re: Neutts-air – Open-source, on device TTS
#15BTW I was looking to train a TTS on my voice, whats the best way to do that today locally?
Re: Neutts-air – Open-source, on device TTS
#16Tangential, how easy is it to verify watermark with a smartphone and how easy is it to erase the watermark?
Re: Neutts-air – Open-source, on device TTS
#17Re: Neutts-air – Open-source, on device TTS
#18Re: Neutts-air – Open-source, on device TTS
#19> 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
Re: Neutts-air – Open-source, on device TTS
#20Need to hook this up to Home assistant