No subscriptions. No retainers. Pick the plan that fits the project — your voice clone stays accessible for re-renders.
24–48 hours
Hear your voice clone before you commit
2–3 business days
Polished narration for short fiction or scripts
5–7 business days
Full-length audiobook, broadcast-ready
Full Service
7–10 business days
Production, mastering and platform delivery
Showing all 4 plans
You upload a clean 30–90 second voice sample (or pick a library voice). Our pipeline uses ElevenLabs and PlayHT models to build a vocal fingerprint, then synthesizes long-form audio chapter by chapter while preserving your prosody, accent and breath patterns.
We accept PDF, DOCX and plain TXT manuscripts up to 25 MB. For best results submit a clean reading copy with chapter headings clearly marked.
No. You can only clone voices you have explicit, written permission to use. Our terms require proof of consent for any non-library voice. We will reject submissions that violate this.
Every order is processed through an iZotope RX + Ozone chain — noise reduction, de-essing, EQ, dynamics, loudness normalization to -23 LUFS and a -3 dB peak ceiling so it meets ACX and Findaway technical standards out of the box.
You receive a ZIP containing per-chapter MP3 files, a single bundled M4B (audiobook format) and a re-render guide PDF. Higher tiers also include WAV stems and a metadata sheet.
Short Story and above include voice-clone access for a defined window. The included PDF guide explains exactly how to log in, paste new text and re-render specific chapters yourself.
