Accepted voice names

The other voice names POST /v1/audio/speech accepts, and the Paxa voice that speaks each one.

View as Markdown

Besides Paxa voice ids, POST /v1/audio/speech accepts the names below. The Paxa voice beside each name speaks it, and the response names the voice that spoke in its x-voice-id header.

NamePaxa voice
alloyFoi Thong (foithong)
ashKhanom Krok (khanomkrok)
balladOliang (oliang)
cedarKhao Tom (khaotom)
coralCookie (cookie)
echoMassaman (massaman)
fableEspresso (espresso)
marinSalim (salim)
novaNom Yen (nomyen)
onyxThong Ek (thongek)
sageBai Toey (baitoey)
shimmerTako (tako)
verseLatte (latte)

A name resolves on any model that serves its voice, and paxa-tts-flash-v2 serves every voice here. A Paxa voice id always takes precedence. A name that is neither a Paxa voice id nor in this table answers 400 unknown_voice. GET /v1/voices lists every Paxa voice.