Good quality but unfortunately it is single language English only.
Pocket TTS: A high quality TTS that gives your CPU a voice
11–20 of 164 posts
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#12Good quality but unfortunately it is single language English only.
I echo this. For a TTS system to be in any way useful outside the tiny population of the world that speaks exclusively English, it must be multilingual and dynamically switch between languages pretty much per word.
Cool tech demo though!
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#13Nice!
Just made it an MCP server so claude can tell me when it's done with something :)
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#14Is there something similar for STT? I’m using whisper distill models and they work ok. Sometimes it gets what I say completely wrong.
from the other day https://github.com/cjpais/Handy
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#15Love 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.
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#16I love that everyone is making their own TTS model as they are not as expensive as many other models to train. Also there are plenty of different architecture. Another recent example: https://github.com/supertone-inc/supertonic
In-browser demo of Supertonic with WASM:
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#17Oh this is sweet, thanks for sharing! I've been a huge fan of Kokoro and event setup my own fully-local voice assistant [1]. Will definitely give Pocket TTS a go! [1] https://github.com/acatovic/ova
Kokoro is better for tts by far
For voice cloning, pocket tts is walled so I can't tell
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#18>If you want access to the model with voice cloning, go to https://huggingface.co/kyutai/pocket-tts and accept the terms, then make sure you're logged in locally with `uvx hf auth login`
lol
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#19Is there something similar for STT? I’m using whisper distill models and they work ok. Sometimes it gets what I say completely wrong.
Parakeet is not really more accurate than Whisper, but it's much faster - faster than realtime even on CPU: https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3 . You have to use Nemo though, or mess around with third-party conversions. (Also has a big brother Canary: https://huggingface.co/nvidia/canary-1b-v2. There's also the confusingly named/positioned Nemotron speech: https://huggingface.co/nvidia/nemotron-speech-streaming-en-0...)
Re: Pocket TTS: A high quality TTS that gives your CPU a voice
#20Good quality but unfortunately it is single language English only.
I echo this. For a TTS system to be in any way useful outside the tiny population of the world that speaks exclusively English, it must be multilingual and dynamically switch between languages pretty much per word. Cool tech demo though!
That's a pretty crazy requirement for something to be "useful" especially something that runs so efficiently on cpu. Many content creators from non-english speaking countries can benefit from this type of release by translating transcripts of their content to english and then running it through a model like this to dub their videos in a language that can reach many more people.