Vaakini docs

Voices and options

Voices and languages

The voices you can speak with, how to list them, and the twelve languages the model speaks.

View as Markdown

Voices#

Pass a voice’s name as voice, in any case: Monika and monika are the same voice.

voiceMade forGenderDescription
BuntyHindiMaleYoung male voice, friendly, casual
MonikaHindiFemaleYoung female voice, warm, helpful
UmanandaAssameseMaleAdult male voice, steady, friendly
RimjhimBengaliFemaleYoung female voice, clear, expressive
MuskanGujaratiFemaleAdult female voice, warm, sweet
SrivatsaKannadaMaleAdult male voice, casual, natural
MahendranMalayalamMaleYoung male voice, relatable, natural
SunainaMalayalamFemaleAdult female voice, warm, clear
AmoghMarathiMaleYoung male voice, casual, engaging
KalyaniMarathiFemaleYoung female voice, warm, gentle
SwastikOdiaMaleAdult male voice, casual, warm
RaqibPunjabiMaleYoung male voice, warm, conversational
VennilaTamilFemaleYoung female voice, warm, easygoing
BhaavanaTeluguFemaleYoung female voice, natural, warm

Each voice is made from a recording in its own language, and can speak the other eleven too. Hear them all in the dashboard’s playground.

Your org can also have voices of its own, each from a short recording: custom voices, spoken by their id (cv_…).

Listing voices#

GET /v1/voices answers the voices your org can speak with: ours, then your custom voices.

curl https://api.vaakini.com/v1/voices \  -H "Authorization: Bearer $VAAKINI_API_KEY"
{  "voices": [    {      "id": "Monika",      "name": "Monika",      "category": "builtin",      "gender": "female",      "description": "Young female voice, warm, helpful",      "languages": ["hi"]    },    {      "id": "cv_t76u7a3um3xayk4b",      "name": "Priya (support)",      "category": "cloned",      "gender": "female",      "description": null,      "languages": ["hi"]    }  ]}

id is what voice takes. category is builtin for one of ours and cloned for a custom voice. languages is the language the voice is made for. The list is the one to trust: a voice added since this page was written is in it. GET /v1/models, which needs no key, lists our voices’ names alone.

Languages#

language says which language the text is in. It is optional.

languageLanguage
asAssameseঅসমীয়া
bnBengaliবাংলা
enEnglishEnglish
guGujaratiગુજરાતી
hiHindiहिन्दी
knKannadaಕನ್ನಡ
mlMalayalamമലയാളം
mrMarathiमराठी
orOdiaଓଡ଼ିଆ
paPunjabiਪੰਜਾਬੀ
taTamilதமிழ்
teTeluguతెలుగు

Left out, the model picks the language from the script of each sentence. Name it when you know it: with normalization on, numbers, dates and amounts are read aloud in the request’s language.

Any voice can be combined with any language.

Write each word in its own script#