search

rhasspy / piper

A fast, local neural text to speech system
https://rhasspy.github.io/piper-samples/
MIT License
4.57k stars 315 forks source link

support for --phoneme-input for having pure phonemes as input #403

Open contentnation opened 3 months ago

contentnation commented 3 months ago

Feature to have pure phonemes as input, instead of text. Can be (ab)used to create language mixing. Example: echo -n -e "ðɪs ɪz ˈɪŋɡlɪʃ wɪð ɐ fɹˈɛntʃ ˈaksənt" | piper -p -m fr_FR-upmc-medium "This is english with a french accent" spoken by a french voice.

fullymiddleaged commented 1 month ago

Nudge, does this work now?

contentnation commented 1 month ago

@fullymiddleaged it works for me, if you have any cases where it breaks, please report it so it can be fixed.

fullymiddleaged commented 1 month ago

@fullymiddleaged it works for me, if you have any cases where it breaks, please report it so it can be fixed.

Oh, okidoke, I'll try again!