News for hackers. Stuff that matters.
Re:Speech Synthesis on Linux (2020) by synesthesiam on Saturday September 25, 2021 @11:17AM (#28653784)
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 :)

Re:Speech Synthesis on Linux (2020) by dm319 on Saturday September 25, 2021 @02:22PM (#28655085)
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'".

Re:Speech Synthesis on Linux (2020) by synesthesiam on Saturday September 25, 2021 @03:11PM (#28655458)
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
Re:Speech Synthesis on Linux (2020) by c6401 on Saturday September 25, 2021 @10:59PM (#28658069)
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.
Re:Speech Synthesis on Linux (2020) by synesthesiam on Sunday September 26, 2021 @08:32AM (#28660380)
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.

Re:Speech Synthesis on Linux (2020) by c6401 on Sunday September 26, 2021 @03:22PM (#28663764)
Thank you! Streaming output to aplay works pretty well for me.
Re:Speech Synthesis on Linux (2020) by tailspin2019 on Saturday September 25, 2021 @01:16PM (#28654677)
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!

Re:Speech Synthesis on Linux (2020) by synesthesiam on Saturday September 25, 2021 @01:58PM (#28654931)
Thanks! They seemed to work fine with en_us phonemes, so I haven't created a separate en_gb set yet. Maybe someday :)
Re:Speech Synthesis on Linux (2020) by posguy on Saturday September 25, 2021 @07:01PM (#28656910)
cmu_jmk (glow_tts) under en_us seems to be quite nice
Re:Speech Synthesis on Linux (2020) by c6401 on Saturday September 25, 2021 @09:55PM (#28657729)
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.
Re:Speech Synthesis on Linux (2020) by FeepingCreature on Saturday September 25, 2021 @03:49PM (#28655725)
Sweet, I've been hoping for good Linux TTS!
Re:Speech Synthesis on Linux (2020) by phkahler on Saturday September 25, 2021 @11:49AM (#28654021)
Can it run on a raspberry pi?
Re:Speech Synthesis on Linux (2020) by synesthesiam on Saturday September 25, 2021 @12:02PM (#28654148)
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).
Re:Speech Synthesis on Linux (2020) by moffkalast on Saturday September 25, 2021 @07:34PM (#28657056)
That's fantastic, someone ought to integrate this with Mycroft, stat.