Professional voice cloning trains a highly natural-sounding voice model to sound just like you, delivering a voice so authentic your listeners will feel like they’ve got their favourite author in their pocket.

A professional voice clone will mirror the speaker data it is trained on. For an optimal clone, we require speakers to record a tailored script, such as articles, to ensure the model captures your desired speaking style.

See supported languages and accents.

Record 10 articles

Clone a voice with just 10 article recordings or 30 minutes of audio.

Ready in 24 hours

Get a highly natural voice clone within one day.

Hyper-realistic

Generate audio so authentic listeners will feel like they have their favorite author in their pocket.

Custom pronunciations

Our Professional Voice Clones support full pronunciation customization—including IPA—across all languages.


​
Create a professional voice clone

Professional voice cloning isn’t available through self-service just yet - but we’ll guide you through the process.
To get started, please book a meeting or email support@beyondwords.io.

1

Book a meeting

  • Book a meeting or reach out to our team.
  • We’ll discuss your goals for the voice and walk you through each step of the cloning process.
2

Share 10-15 articles

  • We believe voices sound best when trained on content that’s authentically yours.
  • Share 10 to 15 published articles - a Word doc is totally fine. We’ll use these to create a customised recording script for your speaker.
3

Share your voice details

  • We’ll need your speaker’s first and last name - this is required so they can record the voice cloning consent statement, which gives us permission to clone their voice.
  • You can also give the voice a name - this helps you find and manage it in the platform later.
  • Once we have these details, we’ll send you a link to the recording script where you can upload the recordings.
4

Record and upload

  • Your speaker will record both the script and the consent statement.
  • We’ll provide simple recording guidelines and audio requirements to help you get the best results.
  • Once recordings are complete, just upload the files and click “Submit.”
5

Training

  • Now it’s over to us.
  • Voice training typically takes 1-2 days, after which we’ll review and deploy it to your account.
6

Use your voice

  • We’ll let you know as soon as the voice is ready.
  • You can then start turning articles into audio using your new, professionally cloned voice.

​
Recording tips

The voice clone will accurately replicate the style and performance of the speaker. For this reason, it is important that each article is recorded with the same energy, pace, and style that you would like the voice clone to have.


​
Recording requirements

Save each file as an individual .wav audio file then upload it under the words of each article in the script recording interface. Optimum recordings are:

  • File format: *.wav, Mono
  • Sampling rate: Minimum of 22 kHz for clear audio capture.
  • Sample format: Minimum of 16-bit PCM (uncompressed) for lossless audio quality.
  • Volume levels: Between -23dB and -18dB RMS across the recording, with a maximum peak of -3dB to avoid clipping and distortion.
  • Signal-to-noise ratio (SNR): Greater than 35dB (higher is better) for minimal background noise.
  • Environment noise, echo: Background noise level before speaking should be less than -70dB for optimal clarity.
  • Send us the files as “unprocessed” as possible: e.g. do not apply filters, compression, limiters and the like. We’ll standardise your files in-house to ensure optimal settings perfect for voice cloning