Skip to content
Blog
Voices8 minutes read

Twenty Seconds Is Enough: What Our Best Author Voice Clones Were Recorded On

Published Updated
DM

David Mainayar

Co-founder & CEO

Share this article


Bone paper timeline with 20s marked enough
Summary

Four author clones, input and output. The 20-second clip each author sent, the clone reading their book, and the recording rules that held.

Our current clone path needs about twenty seconds of you talking. A phone and a furnished room are enough. Below are four author clones we shipped in September 2026: the exact clip each author gave us, and the clone reading their book. Then the short list of what those clips had in common.

Key numbers: one clip, 20 to 25 seconds, one voice, no music. Peaks under −3 dB. A phone is fine. Levels on the four clips below ranged from −29 to −18 dB RMS and every one of them cloned.

Four clones, input and output

Left is what the author sent. Right is the clone, voice only, reading the opening of their book. Shared with each author's permission. More finished books are on our voice clone samples page.

Jeremy Dyer, The Fundamental Investor

Twenty seconds of Jeremy talking. Full chapters are now in production on this voice.

Jeremy's clip, 20 s
Clone reading chapter one

Mitra Manesh, The Attentionist

Twenty-one seconds cut from a welcome video she had already published. No new recording.

Mitra's clip, 21 s (from her video)
Clone reading the sample

Alan Berg, AI For The Real World

Twenty-one seconds from his podcast. The same clone then read his Spanish title, Ghosting, ¿por qué me ignoran?

Alan's clip, 21 s (from his podcast)
Clone reading in English
Same clone reading in Spanish

Antony Hylton, Biblical Digital Marketing

Twenty-one seconds, British English. The hottest clip of the four (peaks at −0.1 dB). It still cloned, and we would still ask for 3 dB less.

Antony's clip, 21 s
Clone reading the preface

What the four clips had in common

  • One voice, start to finish. No co-host or intro music. No kid in the hallway.
  • Continuous talking. Twenty seconds of actual speech, with no long gaps.
  • The register of the book. Jeremy talks like a founder. Alan talks like a speaker. The clone copies the delivery it hears, so talk the way you want the book read.
  • Nothing fancy. Phone recordings and straight cuts from existing media. Two of the four came off a podcast and a video, and the model still learned the person's voice through the compression.

Level was the least consistent thing across the four and it mattered least. Noise and music are what break a clone. Level is a fader.

How to record it on a phone

This is the direction our engineer gives every author. It fits on a sticky note.

  1. Use the phone's own mic and leave the earbuds out. Hold it 20 to 30 cm from your mouth, USB-C or charging port pointed at your face. The good mic is at the bottom.
  2. Avoid small hard rooms. A bathroom or an empty closet gives you slap. A bedroom or living room with a bed, sofa, curtains, rug soaks reflections. Sit near the soft stuff. Do not chase a perfect room; a bit of reverb on a well-placed mic is fixable.
  3. Turn everything off. Fan, AC, dishwasher, notifications. Windows shut.
  4. One take, 20 to 30 seconds, talking like you would read the book. A paragraph from your first chapter is ideal. Do not whisper, do not announce.
  5. Listen back once. If you hear room noise or your voice pumping up and down, move and redo it. Do not try to fix it in an app.
  6. Send the original file. Email or Drive is fine, and so is our intake link. Do not forward it through a messaging app; messaging apps can recompress voice notes.

Have a real mic? Point it at your mouth

One author sent us a podcast recorded on a broadcast dynamic mic that would embarrass most studios. Our engineer watched thirty seconds of the video and found the problem in one line: the mic was pointed at his desk. Everything else followed from that. He had cranked the input gain to make up for it, the gain pulled in the room, and the voice sat thin under it.

The fix, verbatim from that thread:

  • Mic pointed at your mouth, 5 to 7 inches away. Two to three inches sounds better and clips more. Play it safe.
  • Lower the input gain. If you have been recording off-axis, your gain is set for a mic that is pointing away. Point it at you and bring the gain down until peaks sit around −6 dB.
  • The furnished room is fine. Bed, sofa, curtains, rug, done. If moving to another room is a hassle, do not move. Placement is the problem. The room is fine.
  • Reverb is fixable after the fact. Placement has to be right at the mic. A well-recorded voice with some room on it cleans up into a good clone. A voice recorded off-axis with the gain cranked does not.

Same rule for your phone or a USB mic. The capsule has a front. Find it and talk into it.

Already on tape? Use that

If you have a podcast, a YouTube intro, a webinar, a voice note to a friend, cut twenty seconds where only you speak and nothing plays under you. Two of the four clones above were built that way. The cut matters more than the source: no music bed under you, and no crosstalk or applause.

What kills it

  • Music or a bed under your voice.
  • A second voice anywhere in the clip.
  • A mic pointed somewhere other than your mouth.
  • Bathroom or empty-room echo. Mild reverb in a furnished room is fine.
  • Auto-gain pumping (phone voice memo apps do this when you move).
  • Whispering half and projecting half.
  • Reading in a voice you would never narrate in.

Twenty seconds means one bad second is five percent of the sample. Cut it out, or record again.

Longer samples

Twenty seconds gets you a production clone, and it is what every author above started with. If you want to record more, the long-form brief still applies and helps on pronunciation and retakes. It is not required to start.

For scale: the quick self-narrate flow takes a 10-second minimum, targets 30 seconds, does better at 90, and caps at about two minutes (instant-clone guide). A full production sample for partner narrators runs one to two hours. You can record your clone sample in the browser, upload a file, or paste a YouTube link.

Send your book and a twenty-second clip through the author portal and you hear it in your own voice. No clip yet? Start with a free sample on a cast voice and record later.

FAQ

How long should a voice clone sample be?

Twenty seconds of continuous, clean speech. That is what every clone above was built on, and it gets you a production clone. The quick self-narrate flow takes a 10-second minimum, so treat ten seconds as the floor. Longer only helps if it stays clean. In a twenty-second clip, one bad second is five percent of the sample.

Can I record a voice clone sample on my phone?

Yes. The four clips above include phone recordings, and every one of them cloned. Use the phone's own mic and hold it 20 to 30 cm from your mouth, charging port pointed at your face, because the good mic is at the bottom. Sit in a furnished room near the bed or sofa. Avoid bathrooms and empty closets.

What should I read for my voice clone sample?

A paragraph from your first chapter is ideal. Read it in one take of 20 to 30 seconds, the way you want the book read, because the clone copies the delivery it hears. Keep one register from start to finish. Whispering half and projecting half breaks the sample, and so does a voice you would never narrate in.

Why does my cloned voice sound echoey or noisy?

The model clones everything it hears, and that includes the room. A bathroom or an empty closet gives you slap, and noise or music under your voice is what breaks a clone. Re-record in a bedroom or living room, close to the soft furnishings. Turn off fans, AC, the dishwasher, and notifications, and shut the windows.

What file format should I send?

Send the original file. WAV at 44.1 or 48 kHz, 24-bit, is ideal. For a 20-second clip, a clean room matters more than format, and high-bitrate M4A or MP3 is fine. Keep peaks under −3 dB. Microsoft's guidance for custom voice samples recommends peak levels of −3 to −6 dB.

Who can use my cloned voice?

Your cloned voice is a private model used only for its book. It is held in Lex's production account only to produce audiobooks you authorize. It is not shared, sold, or reused for other clients. You own the finished masters and commercial rights.

Hear a free sample of your book

Send your book. We cast, direct, and score a short passage and send it back in about a day. No card, yours to keep.

More to read