Skip to main content
POST
/
tts
/
multispeaker
Run Multispeaker TTS Model
curl --request POST \
  --url https://api.vogent.ai/api/tts/multispeaker \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "lines": [
    {
      "text": "<string>",
      "voiceId": "<string>"
    }
  ],
  "voiceOptionValues": [
    {
      "optionId": "<string>",
      "value": "<string>"
    }
  ],
  "format": {
    "outputType": "WAV_PCM16",
    "sampleRate": 24000
  }
}
'
"<string>"

Documentation Index

Fetch the complete documentation index at: https://docs.vogent.ai/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

In the form Bearer <api_key_here>. You can find your api key in your dashboard.

Body

application/json
​
lines
object[]
required

The lines that need to be generated.

​
voiceOptionValues
object[]

An optional configuration for the voices being used.

​
format
object

The output format for the generated audio. Defaults to WAV_PCM16 at 24000 Hz.

Response

Returns a file with the audio.

The response is of type file.