ElevenLabs Professional Voice Clone: own voice only, 24 h retry

ElevenLabs allows a Professional Voice Clone only of your own voice: its docs say that even with someone's consent you cannot clone another person's voice. Before training you pass a verification step, and if it fails you wait 24 hours or contact support, per the Professional Voice Cloning page (read 2026-10-02).

Sume has no verification step and no professional-clone tier; you clone from a short clip in the app.

The ElevenLabs rules

The quickstart lists eight steps, from creating the voice and uploading audio to speaker separation, a CAPTCHA verification where the voice owner reads text aloud, and training. It says verification is required to confirm you have permission to use the voice.

What Sume offers

Sume's Voices library in the app has a create dialog that takes a name, a gender, a language and an uploaded or microphone-recorded clip. That dialog has no consent-recording step, and the public API has no route that creates a clone.

There is no slot count in the dialog and no multi-hour training queue to wait for. The trade is control: you cannot ask Sume for a 3-hour fine-tune of a voice.

How this changes a project plan

The vendor rules change who can be the narrator.

• Own-voice only is an ElevenLabs rule for PVC. A narrator who is not you must use another route there; on Sume the responsibility to hold the release is yours.
• For a branded voice that must sound identical across a year of content, decide on one stored clip and keep it.
• Narration for video: use the voice id in text to speech, then join the lines with Timeline audio.

Related reading

For the 10-second instant clone side of the same vendor, see Voice clone 10 seconds AI. For the clone route on Sume, see Voice cloning API.