Feature request: Piper Voice-Option to change pitch of the voice.

[unkn0wn]

https://rhasspy.github.io/piper-samp...-libritts-high
the libritts has option to change pitch as seen in the above link. Is it possible to replicate it on calibre?

[kovidgoyal]

I dont see an option to select pitch there only select between different sub voices within the librtts voice. I'ma fraid sub voice selection isnt possible in calibre.

[unkn0wn]

i though p922, p4568, p3615 meant that it was changing the pitch of the voice. Anyhow how is it that libritts contain so many voices within but am not able to use it through calibre.

maybe being able to change pitch could help me reach a perfect voice for my speakers instead of trying to select one from a default set. Is it possible to add such an option to calibre?

[kovidgoyal]

piper doesnt have any pitch control, run

piper --help

and see for yourself.

[unkn0wn]

I see that there is an option to select speaker_id within a voice file like libritts https://github.com/rhasspy/piper#json-input

Maybe we could integrate into calibre to use different speaker_id.. with libritts it would add 900 other high quality voices to english.

Optional fields include:

speaker - string
Name of the speaker to use from speaker_id_map in config (multi-speaker voices only)
speaker_id - number
Id of speaker to use from 0 to number of speakers - 1 (multi-speaker voices only, overrides "speaker")
output_file - string
Path to output WAV file

The following example writes two sentences with different speakers to different files:

{ "text": "First speaker.", "speaker_id": 0, "output_file": "/tmp/speaker_0.wav" }
{ "text": "Second speaker.", "speaker_id": 1, "output_file": "/tmp/speaker_1.wav" }

[kovidgoyal]

Like I said adding support for sub voices is too much work. In any case they arent really useable, they have auto generated names how is an end user supposed to choose one?