Hacker News Reader

Hacker News

Comment by synesthesiam | Hacker News Reader

Full thread

synesthesiam

I created Larynx (https://github.com/rhasspy/larynx) to address shortcomings I saw in Linux speech synthesis:

* Licensing (MIT)

* Quality (judge for yourself: https://rhasspy.github.io/larynx/)

* Speed (faster than real-time on amd64/aarch64)

* Voices/language support (9 languages, 50 voices)

I'm working now on integrating Larynx with speech-dispatcher/Orca. The next version of Larynx will also support a subset of SSML :)

View on HN

Thought I'd give this a go, but getting lots errors along the lines of 'Expected shape from model of {...} does not match actual shape of {...} for output audio. Tried the debian and python methods of installation on an AMD Ryzen X13.

EDIT: despite those errors I can create output.wav. However, interactive mode crashes with "No such file or directory: 'play'".

The shape warnings don't seem to matter (something to do with the onnx runtime). Interactive mode needs sox installed or for you to specify a --play-command

It's super awesome. Just wondering if it can simultaneously use play-command to play sample and in the same time render the next to eliminate pauses? Also wondering if it can work through spd-say (speech dispatcher). I will probably be able to figure out both just checking in case if there are ready solutions.

Thanks! Try the --raw-stream option for listening to long texts: https://github.com/rhasspy/larynx#long-texts

For speech-dispatcher, I'd start a Larynx HTTP server and use curl to get audio. I have an undocumented --daemon flag that does something like this.

Thank you! Streaming output to aplay works pretty well for me.

Some of those sound really good.

I was going to comment that you didn't have any en_gb listed, but it seems there's a bunch under en_us :)

Some rather good brit'ish accents in there me old mate!

Thanks! They seemed to work fine with en_us phonemes, so I haven't created a separate en_gb set yet. Maybe someday :)

cmu_jmk (glow_tts) under en_us seems to be quite nice

I like "ek", but I'm not a native speaker, so my preference for British English voice might not be the same as for anglophones.

Sweet, I've been hoping for good Linux TTS!

Can it run on a raspberry pi?

Yes! There's a Docker image and Debian package for both 32-bit and 64-bit ARM. The 64-bit version is significantly faster (especially with low quality set).

That's fantastic, someone ought to integrate this with Mycroft, stat.

Reply on news.ycombinator.com