Text To Speech

Text to speech using the lucataco/xtts-v2 AI Model.

POST http://localhost:9000/apiv1/replicate/tts

Try it

Text To Speech

cURL

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 \
  --form speaker='@example-file'

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)