POST
/
api
/
v1
/
tts
/
synthesize-sequence
curl --location 'https://app.fluxon.ai/api/v1/tts/synthesize-sequence' \
--header 'Content-Type: application/json' \
--header 'Authorization: metlo.abcdEFGH12345678zyxw' \
--data '[
    {
        "voiceUuid": "29296f0c-6599-4ba5-bbfc-61cc61da4806",
        "text": "This is person 1 speaking",
        "pitch": 100,
        "speed": 100,
        "delayAfter": 0.5
    },
    {
        "voiceUuid": "61b58d9f-b2f5-468c-a081-31d4a90ce983",
        "text": "This is person 2 speaking",
        "pitch": 100,
        "speed": 100,
        "delayBefore": 0.5
    }
]'
{
    "uuid": "3ae32dda-ff9d-450c-bea2-3feb313edb38"
}

Body

voiceUuid
uuid

The id of the voice to use for the synthesis

text
uuid

The text to synthesize

pitch
int

The pitch of the voice to be synthesized

speed
int

The speed of the voice to be synthesized

delayAfter
float

The gap after a synthesized voice. Is optional.

delayBefore
float

The gap before a synthesized voice. Is optional.

Authorization
string

This is the user auth token generated for app.fluxon.ai.

Response

uuid
uuid

The id of the task synthesizing the conversation. This can be fetched by using the API at GET Synthesize Sequence