POST
v1
/
replicate
/
tts
Text To Speech
curl --request POST \
  --url http://localhost:9000/api/v1/replicate/tts \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'text=<string>' \
  --form 'language=<string>' \
  --form cleanup_voice=true

​
Query

​
model
string
default:"lucataco/xtts-v2"
required
The voice model to be used;

​
Body

​
text
string
required
Text to synthesize
​
speaker
file
required
Original speaker audio (wav, mp3, m4a, ogg, or flv)
​
language
string
default:"en"
Output language for the synthesised speech
​
cleanup_voice
boolean
default:"False"
Whether to apply denoising to the speaker audio (microphone recordings)