Create a Digital Human

to create a digital human you will need a user and organisation depending on your organization's type and privileges, you will have access to various head visuals see docid\ a6pxi9wvcn3uxnytwj7ja for more information components all digital humans are made up of the following required components name alias face voice operating mode video streaming prior to starting the creation process, it is important to consider what operating mode your digital human should use this is directly related to the intended use case operating modes digital humans can operate in 5 distinct modes text to video / video specify text for a given digital human, and a video will be generated with the digital human speaking the text the output is an mp4 file open dialogue configure a prompt for a given digital human, and the digital human will be conversational document / knowledge base provide content and configure a prompt, and the digital human will be conversational about the content provided plugin mode leverage a webhook to connect any custom conversational engine or llm to power the conversation of the digital human digital human creation process all digital humans need an existing head visual and voice to see your available head visuals, see docid\ vpzbfsclk26xbcillnvdg and docid\ ujeqesnyxa j9j2 z6jtl documentation names and aliases are free text fields which are used for personalization there are no restictions apart from being required fields use the post /head/create to create digital humans each operation mode requires a different request body (see docid\ qi6kwaiqafhoaqaan5nkg ) doc qa { "headvisualid" "\<stringidretrievablefromlistfaces>", "name" "test qa", "alias" "ai responder", "languagespeechrecognition" "en us", "language" "en us", "operationmode" "doc qa", "promptconfig" { "system prompt" "string" }, "ttsprovider" "elevenlabs", "ocprovider" "playground", "ttsvoice" "jessica eleven turbo v2 5", "greetings" "hi there!", "videostreaming" true, "phrases" \["unith","barcelona"], "customwords" {"barcelona" "barthelona","ai" "a eye"} } ttt { "headvisualid" "\<stringidretrievablefromlistfaces>", "name" "ttt", "alias" "repeater", "languagespeechrecognition" "en us", "language" "en us", "ttsprovider" "audiostack", "operationmode" "ttt", "ocprovider" "playground", "ttsvoice" "coco", "greetings" "i repeate what you say!" } oc { "headvisualid" "\<stringidretrievablefromlistfaces>", "name" "testoc", "alias" "open ai salesperson", "languagespeechrecognition" "en us", "language" "en us", "operationmode" "oc", "promptconfig" { "system prompt" "string" }, "ttsprovider" "elevenlabs", "ocprovider" "playground", "ttsvoice" "jessica eleven turbo v2 5", "greetings" "hi there!", "videostreaming" true, "phrases" \["unith","barcelona"], "customwords" {"barcelona" "barthelona","ai" "a eye"} } voiceflow { "headvisualid" "\<stringidretrievablefromlistfaces>", "name" "guide", "alias" "ai guider", "languagespeechrecognition" "en us", "language" "en us", "ttsprovider" "audiostack", "operationmode" "voiceflow", "voiceflowapikey" "string", "ocprovider" "playground", "ttsvoice" "coco", "greetings" "hi there!" } plugin { "headvisualid" "\<stringidretrievablefromlistfaces>", "name" "guide", "alias" "ai guider", "languagespeechrecognition" "en us", "language" "en us", "ttsprovider" "elevenlabs", "ocprovider" "playground", "videostreaming" true, "ttsvoice" "jessica eleven turbo v2 5", "operationmode" "plugin", "pluginoperationalmodeconfig" { "name" "\<plugin name>", "url" "\<plugin url>", "options" { "\<optional param>" "option value" } }, "greetings" "hi there!" } the payload can contain many additional properties of the digital human as described in the docid\ qi6kwaiqafhoaqaan5nkg page if you have access to multiple organsations, you will need to add "orgid" "\<orgid>" to the payload please note that voiceflow is not a actively maintained mode anymore request body parameters true 202,125,415left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left unhandled content type left 1 1 unhandled content type left 1 1 unhandled content type left 1 1 unhandled content type by default, all digital humans are created in streaming mode if you want to create a legacy, non streaming digital human, you need to include videostreaming=false in your payload example requests curl x 'post' \\ 'https //platform api unith ai/head/create' \\ h 'accept application/json' \\ h 'authorization bearer \<yourbearer>' \\ h 'content type application/json' \\ d '{ "headvisualid" "abc123abc123", "name" "ttt", "alias" "repeater", "languagespeechrecognition" "en us", "language" "en us", "ttsprovider" "elevenlabs", "videostreaming" true, "operationmode" "ttt", "ocprovider" "playground", "ttsvoice" "coco eleven turbo v2 5" }' knowledge base ( doc qa ) digital humans need an additional step to be functional this is described in docid 0d qdu8wz5ugua deosea and related to uploading a knowledge document interact with a digital human upon creating a digital human with a single call to the head/create endpoint, your digital human is now hosted by unith this url can be found in the post head/create response public url { "publicid" "headid", "publicurl" "https //stream unith ai/\[org id]/\[head id]?api key=\[org api key]", }