logoalt Hacker News

drum55 • today at 4:27 PM • 9 replies • view on HN

Closed model unfortunately, continues the theme of TTS / STT being really not great for local deployments.


Replies

dr_hooo • today at 5:04 PM

Too bad it's not open, unlike the previous version.

However, I found Qwen ASR and QwenTTS to be quite good, and not too large. Also https://github.com/kyutai-labs/pocket-tts was also great (but only a few languages)

➕ show 1 reply
gavinray • today at 5:45 PM

Best sounding local TTS engine I've heard by far is Kokoro

It's small enough to be run on modern phones realtime, I use it for listening to PDF's/EPUB as Audiobooks

https://huggingface.co/hexgrad/Kokoro-82M

➕ show 1 reply
IsaacZerh • today at 5:02 PM

Funny because Gradium just released a local TTS that runs on many devices

https://x.com/GradiumAI/status/2112563128487514512?s=20

➕ show 2 replies
aliljet • today at 4:37 PM

What options would you run locally at this stage? I'm finding a ton of success with local models in this space ..

➕ show 4 replies
arendtio • today at 6:26 PM

My favorite so far is https://speaches.ai

Not because of the models, but because it comes in a nice (easy-to-set-up) package, and the latency was lower than I expected with such a setup.

c0rruptbytes • today at 8:55 PM

Omnivoice is pretty good

causal • today at 4:34 PM

> Available via Mistral’s EU-hosted API or self-deployment

What does this mean then?

➕ show 1 reply
j-pb • today at 4:35 PM

Breeze is pretty good imho.

Mashimo • today at 4:43 PM

Dang, this could have been fun for home assistent.