Voice

Clone a voice

Your own voice (or the voice of someone who agreed) as a new voice for voice-overs: send 1–5 recordings of that one person — 1–3 minutes in all, clean, no music — and the consent declaration. Returns a voice_id that only your account can use: POST /v1/ai/voice with it (model eleven_v4 speaks Hebrew with the most emotion; audio tags like [excited] direct it). Recordings in the language you will speak clone best. A recording the provider flags for the speaker's own verification is refused and nothing is kept. Delete a voice you no longer need with DELETE /v1/ai/voices/{voice_id}.

Billing: One clone (a voice slot); every voice-over with it is priced as usual · Rate limit: 5/min

post/v1/ai/voices/clone

Request

  • Base URL: https://apihub.co.il
  • URL: https://apihub.co.il/v1/ai/voices/clone
  • Auth: HTTP bearer

Headers

Idempotency-Keystring

Replay-safe: the same execution is returned instead of charging twice

X-Tagstring

Group calls into one job (e.g. one video) — see GET /v1/usage?tag=…

Request body

namestring required

The voice's name in your list

languagestring

The recordings' language (he, en, ru…)

audio_urlsstring[] required

1–5 recordings of the SAME person speaking (mp3, wav, m4a, ogg, flac): 1–3 minutes in all, clean, no music, one speaker. A video? Take its sound first: POST /v1/studio/convert with output.format "mp3"

consent_idstring

A consent you recorded before (the dashboard records one when you tick the box)

descriptionstring
remove_background_noiseboolean

Clean the recordings before cloning (leave it on unless the recording is studio-clean)

Response

Completed

idstring

Execution id — stable across internal retries; use it with GET /v1/executions/{id}

status'pending' | 'processing' | 'completed' | 'partial' | 'failed' | 'cancelled' | 'timeout'
operationstring
tagstring nullable

Your X-Tag, if sent

created_atstring date-time
completed_atstring date-time nullable
outputobject

Operation result (see each operation). While a Studio render is processing: stage (queued · transcribing · downloading · preparing · cleaning_voice · mixing_audio · rendering · finishing), phase (the engine's: download · prepare · voice · audio · encode · qa · upload, or null), progress (a percent, 0–100) and progress_fraction (0–1), eta_seconds (seconds left, never below 0) and estimate_seconds

errorstring nullable

Changes

No recorded changes to this operation across all 2 revisions of this API.