Hi Matthew, thanks for the request. An ElevenLabs integration for voice cloning makes sense, especially if you already have a trained voice model and want consistency across recordings.

To scope this properly, can you share a bit more about your ideal workflow?

1) Where would you want to use the cloned voice in Sendspark: new video recordings, voiceovers on existing videos, or both?

2) Do you want the voice generated from typed text (text to speech), or are you looking to transform your own recorded audio into your cloned voice?

3) Which ElevenLabs setup are you using today (Instant Voice Cloning vs Professional Voice Cloning), and do you already have API access enabled?

4) How should we handle voice selection: one default voice per workspace, per user, or selectable per video?

5) Any requirements around consent and compliance (for example, restricting who can use a cloned voice, audit logs, or approvals)?

6) What output quality and turnaround time do you need (real time preview vs background generation)?

If you can also share a quick example of a use case (sales outreach, support follow ups, onboarding, etc.) and roughly how many videos per week you would generate with the cloned voice, that will help us prioritize and design the right version of this.

Once we have those details, we can outline what an initial integration would look like and what it would take to ship a first iteration.