Custom Voices

Create Instant Clone

SDK

Use the SDK for safer, faster integration than manual HTTP calls.

Creates a synthesis-ready custom voice from one WAV or MP3 recording. Send the audio, a display name, and a supported TTS model as multipart/form-data.

Audio requirements

One WAV or MP3 file
File size: 25 MiB or less
Duration: 5 to 150 seconds

The request uses one custom voice slot. A successful response returns the completed voice immediately. Supported models may vary by account and release availability.

POST/v1/custom-voices/instant-clone

cURL

curl --request POST \
  --url https://api.typecast.ai/v1/custom-voices/instant-clone \
  --header 'X-API-KEY: <api-key>' \
  --form 'file=@voice-sample.wav' \
  --form 'name=Product Narrator' \
  --form 'model=ssfm-v30'

{
  "name": "Product Narrator",
  "model": "ssfm-v30",
  "status": "completed",
  "voice_id": "uc_6700000000000000000000aa"
}

Authorizations

X-API-KEYstringheaderrequired

API key for authentication. You can obtain an API key from the Typecast API Console.

Body

multipart/form-data

Multipart request body for instant voice cloning.

filestringrequired

One WAV or MP3 recording, 25 MiB or less and 5 to 150 seconds long.

namestringrequired

Voice name, up to 30 characters.

modelssfm-v30 | ssfm-v21required

TTS model version.

ssfm-v30ssfm-v21

Response

201Instant clone created successfullyapplication/json

namestring

Voice name.

modelstring

TTS model version.

statuspending | training | completed | failed

Current creation or training status.

pendingtrainingcompletedfailed

voice_idstring

Unique custom voice identifier with the uc_ prefix.

cURL

curl --request POST \
  --url https://api.typecast.ai/v1/custom-voices/instant-clone \
  --header 'X-API-KEY: <api-key>' \
  --form 'file=@voice-sample.wav' \
  --form 'name=Product Narrator' \
  --form 'model=ssfm-v30'

{
  "name": "Product Narrator",
  "model": "ssfm-v30",
  "status": "completed",
  "voice_id": "uc_6700000000000000000000aa"
}