Cybervox is the CyberLabs voice solution platform. Using Deep Learning techniques, we develop voice solutions in Brazilian Portuguese that are state of the art in Artificial Intelligence.
For a working example follow the links bellow.
This is the documentation for version 1.0.0
of the API. Last update on Apr 28, 2021.
https://api.cybervox.aicurl --request POST \
--url https://api.cybervox.ai/auth \
--header 'content-type: application/json' \
--data '{"client_id":"(( your client id ))","client_secret":"(( your secret ))","audience":"https://api.cybervox.ai","grant_type":"client_credentials"}'
{
"access_token": "(( jwt token ))",
"token_type": "Bearer"
}
Check the jwt token expiration time (exp) and only get a new one when necessary!
curl --request GET \
--url https://api.cybervox.ai/.../?access_token=(( jwt token ))
Please note this is a websocket api (wss://). After connecting to the websocket, send the described request.
To listen to the generated audio, use the audio_url returned on the response's payload field:
https://api.cybervox.ai + (( audio_url ))response{
"emit": "tts",
"payload": {
"text": (( string: text to be converted )),
"voice": (( string: voice used to generate the audio )),
"timestamp": (( number: Date.now() ))
}
}
{
"event": "tts",
"payload": {
"success": (( bool )),
"reason": (( string )),
"audio_url": (( string )),
"timestamp": (( number ))
}
}
echo '{"emit":"tts","payload":{"text":"ola mundo"}}' | \
websocat -n1 'wss://api.cybervox.ai/ws?access_token=(( jwt token ))'
> {"event":"tts","payload":{"success":true,"reason":"","audio_url":"/play/(( upload_id ))"}}
Please note this is a websocket api (wss://). After connecting to the websocket, send the described request.
{
"emit": "upload",
"payload": {
"max_uploads": 1,
"timestamp": (( number: Date.now() ))
}
}
... followed by the audio file contents (websocket binary message)
{
"event": "upload",
"payload": {
"upload_id": (( string ))
"timestamp"`: (( number ))
}
}
websocat, the tool we used has no support for text + binary websocket messages
Please note this is a websocket api (wss://). After connecting to the websocket, send the described request.
upload action.{
"emit": "stt",
"payload": {
"upload_id": (( string: upload_id received from upload action ))
"timestamp": (( number: Date.now() ))
}
}
{
"event": "stt",
"payload"`: {
"success": (( bool )),
"reason": (( string )),
"text": (( string )),
"timestamp": (( number ))
}
}
echo '{"emit":"stt","payload":{"upload_id":"..."}}' | \
websocat -n1 'wss://api.cybervox.ai/ws?access_token=(( jwt token ))'
> {"event":"stt","payload":{"success":true,"reason":"","text":"..."}}
You should upload at least 4 audio files using the upload action.
The first audio of the upload batch will be compared with the remaining ones assuming they are from the same person.
Please note this is a websocket api (wss://). After connecting to the websocket, send the described request.
upload action (with at least 4 audio/voice files).{
"emit": "voxid",
"payload": {
"upload_id": (( string: upload_id received from upload action ))
"timestamp": (( number: Date.now() ))
}
}
{
"event": "voxid",
"payload"`: {
"success": (( bool )),
"reason": (( string )),
"score": (( float )),
"timestamp": (( number ))
}
}
echo '{"emit":"voxid","payload":{"upload_id":"..."}}' | \
websocat -n1 'wss://api.cybervox.ai/ws?access_token=(( jwt token ))'
> {"event":"voxid","payload":{"success":true,"reason":"","score":"..."}}
The credentials to validate.
curl \
-X POST https://api.cybervox.ai/auth \
-d '{"client_id":"string","client_secret":"string","audience":"string","grant_type":"string"}'{
"client_id": "string",
"client_secret": "string",
"audience": "string",
"grant_type": "string"
}Empty 200 response to check if service is available.
This API should not be directly called.
It's meant to be used by internal tooling.
curl \
-X GET https://api.cybervox.ai/hcThe audio uuid returned by the websocket.
curl \
-X GET https://api.cybervox.ai/play/{audio_uuid}curl \
-X GET https://api.cybervox.ai/ws