Text to speech

Clone a voice

Clone a voice from an uploaded audio sample. This is a multipart/form-data upload that starts a background cloning job and returns immediately with a voice_id. The voice is not usable right away — it becomes available once its is_ready flag turns true. Poll GET /api/ext/tts/voices or GET /api/ext/tts/voices/{voice_id} to check readiness before using the new voice for TTS or agents.

POST

https://api.nabrah.ai/api/ext/tts/clone_voice

Clone a voice

curl --request POST \
  --url 'https://api.nabrah.ai/api/ext/tts/clone_voice' \
  --header 'X-API-Key: <your-api-key>'

{
  "success": false,
  "message": "string",
  "voice_id": "string"
}

Multipart form fields

Send the request as multipart/form-data (not JSON).

file

The audio sample to clone, uploaded as a WAV file.

name

A human-readable display name for the new voice.

Response & next steps

On success the endpoint returns the cloning job result.

voice_id

The id of the newly created private voice. Use this to poll for readiness and, once ready, as the voice field in TTS generation.

success / message

Status flag and human-readable message describing the outcome of starting the cloning job.

successmessage

Cloning runs in the background. The new voice will report is_ready: false until processing completes — poll GET /api/ext/tts/voices/{voice_id} until it is true.

Authorization

X-API-Keystringheaderrequired

Your workspace API key. Create one in the dashboard under API keys.

Body

multipart/form-data

Response

200

Successful Response

application/json

422

Validation Error

application/json