TTS
Clone Voice
Creates a new voice clone based on an uploaded audio sample. The audio should be clear and contain at least 30 seconds of speech.
POST
/
v1
/
tts
/
clone-voice
Authorizations
X-API-KEY
string
headerrequiredBody
multipart/form-data
audio_clip
file
requiredAudio file containing the voice sample to clone (Supported formats: WAV, MP3, M4A)
name
string
requiredA descriptive name for the cloned voice
language
enum<string>
default: enrequiredLanguage of the voice
Available options:
en
, fr
, de
, es
, pt
, zh
, ja
, hi
, it
, ko
, nl
, pl
, ru
, sv
, tr
gender
enum<string>
requiredGender of the voice
Available options:
male
, female
description
string
Additional details about the voice characteristics
Response
200 - application/json
msg
string
err
boolean
results
object
Was this page helpful?