so i yes, espeak exists and still sounds terrible even worse than picoTTS (last update 4 yrs ago?). so what else is there? i look at mimic3 and it says they are dead and one should go for piper here: https://github.com/MycroftAI/mimic3 the link to piper followed I get: https://github.com/rhasspy/piper "This repository was archived by the owner on Oct 6, 2025. It is now read-only. "
ok, so coqui? https://github.com/coqui-ai/TTS no update in over 12 months…how bad can it be? https://coqui.ai/ …great it is a page for gambling now.
so, what are you using? gTTS is not offline.
my use case is that n8n sshs into a remote machine with low specs and a connected speaker to read out information sent from n8n so i can do stuff like:
pico2wave -l de-DE -w /tmp/warn.wav "Es ist {{ $json.Hour }} Uhr." && aplay /tmp/warn.wavAnd as you might have guess by now german language would be appreciated. I’m not going to run any additional docker containers for voice generation or invoke remote services. also the speaker is as dirt cheap as the rest of the setup so any output from espeak was basically killing my eardrums.I’m fairly confident espeak is all you’re going to get that’s FOSS, local, and with any non English support. Yes every espeak language sounds like a Brittish guy badly pronouncing that language, and this includes the American English voice as well.
@ikidd@lemmy.world pointed me to piperTTS and i ended up with a python virtual enviroment, pip install piper-tts and de_DE-thorsten-high.onnx+json to be able to run
echo "{{ $json.state}}" | piper -m ./de_DE-thorsten-high.onnx -f voice.wav && aplay voice.wavand indeed that sounds much better than pico and espeak