Professional voice cloning
Learn how to create a professional voice clone with BeyondWords.
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 5 articles
Clone a voice with just 5 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
Go to the Voice cloning section
Click on the top left menu and select Voice cloning.
Create a Speaker
To create a voice, you need to create a speaker. Click on the ”+ Speaker” button and enter your Speaker’s first and last name.
In the final step, the speaker will need to record a consent statement and their first and last name will be included in it.
Select Instant Voice Cloning
Click on the Speaker, click ”+ Custom voice” and then select Professional voice cloning.
Add voice details
Give your voice a name that will help you identify it in the future. Select the language and accent of the voice you want to clone.
Create a script
Import at least 5 articles to create a recording script. We recommend article-based scripts to ensure the model captures your desired speaking style.
Upload audio
Record or upload a recording of each article in the script.
Consent
Record or upload a voice clip of the speaker recording the consent statement and confirm that you have consent to clone the voice.
The voice clone will only be available to your organization. No one else will be able to see or use it.
Training
Submit the training data to start the training process. You will receive an email when the voice clone is ready to use.
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
We recommend saving each article as an individual .wav audio file.
- 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