Make Overdub’s Speech Synthesis Even Better With These Tips

Last week, we launched Overdub, an AI voice generator that allows you to create a realistic clone of your own voice. To help you make the most of the software, we’re offering some tips to ensure a production-ready Overdub voice, with crisp fidelity, realistic intonation, and natural expressiveness.
August 10, 2020
Chris Zaldúa
In this article
Start editing audio & video
This makes the editing process so much faster. I wish I knew about Descript a year ago.
Matt D., Copywriter
Sign up

What type of content do you primarily create?

Videos
Podcasts
Social media clips
Transcriptions
Start editing audio & video
This makes the editing process so much faster. I wish I knew about Descript a year ago.
Matt D., Copywriter
Sign up

What type of content do you primarily create?

Videos
Podcasts
Social media clips
Transcriptions

Last week, we launched Overdub, an AI voice generator that allows you to create a realistic clone of your own voice. To help you make the most of the software, we’re offering some tips to ensure a production-ready Overdub voice, with crisp fidelity, realistic intonation, and natural expressiveness.

Improve your recording conditions

Your training data should be recorded in a quiet, acoustically “dead” room, and you should be using an external microphone.

Record more training audio

While Overdub voices can be trained with as little as 10 minutes of audio, we recommend at least 30 minutes. The likelihood of a production-ready voice increases as you increase your training data volume, all the way up to 90 minutes.

Open your training data project to record one of our supplemental scripts.

Experiment with Styles

Styles let you copy the various delivery styles of your real audio recordings. Every Overdub is generated using a Style; your voice comes loaded with one as a default. The default style might not be optimal for the content you are creating. To create a new Style, select a range of real audio (complete sentences are recommended) that’s three to twenty-five seconds long, right-click, and select “Save as Style.” Learn more about setting up Styles.

Play with punctuation

Periods and commas affect Overdub intonation. Add and remove them to fine-tune delivery.

“Convert to audio” to tweak timing and boundaries

Right-click on an Overdub (or hover over the clip in the timeline) to convert it to normal Descript audio. Once it’s audio, you can fine-tune the word spacing and sentence boundaries just like any other clip. Learn more about Timeline Editing.

Overdub additional words

If you’re making an editorial correction of a word and it sounds unnatural, undo and experiment with grabbing another word or two on either side.

To change pronunciation, spell a word as it sounds

If Overdub mispronounces a word, try a different (incorrect, but phonetic) spelling. Once you’ve got it sounding right, you can always convert the Overdub to audio (see “Convert to audio” above) to correct the spelling in the transcript.

Ready to try a realistic voice generator for yourself?

Download Descript today and try Overdub for yourself. We have a feeling you’ll be impressed.

Chris Zaldúa
Former marketing writer at Descript. Covers interesting customer stories, product releases, and new ways to utilize Descript to create podcast and video content.
Start creating
The all-in-one video & podcast editor, easy as a doc.
Sign up
Start creating—for free
Sign up
Join millions of others creating with Descript

Make Overdub’s Speech Synthesis Even Better With These Tips

Last week, we launched Overdub, an AI voice generator that allows you to create a realistic clone of your own voice. To help you make the most of the software, we’re offering some tips to ensure a production-ready Overdub voice, with crisp fidelity, realistic intonation, and natural expressiveness.

Improve your recording conditions

Your training data should be recorded in a quiet, acoustically “dead” room, and you should be using an external microphone.

Record more training audio

While Overdub voices can be trained with as little as 10 minutes of audio, we recommend at least 30 minutes. The likelihood of a production-ready voice increases as you increase your training data volume, all the way up to 90 minutes.

Open your training data project to record one of our supplemental scripts.

Experiment with Styles

Styles let you copy the various delivery styles of your real audio recordings. Every Overdub is generated using a Style; your voice comes loaded with one as a default. The default style might not be optimal for the content you are creating. To create a new Style, select a range of real audio (complete sentences are recommended) that’s three to twenty-five seconds long, right-click, and select “Save as Style.” Learn more about setting up Styles.

Play with punctuation

Periods and commas affect Overdub intonation. Add and remove them to fine-tune delivery.

“Convert to audio” to tweak timing and boundaries

Right-click on an Overdub (or hover over the clip in the timeline) to convert it to normal Descript audio. Once it’s audio, you can fine-tune the word spacing and sentence boundaries just like any other clip. Learn more about Timeline Editing.

Overdub additional words

If you’re making an editorial correction of a word and it sounds unnatural, undo and experiment with grabbing another word or two on either side.

To change pronunciation, spell a word as it sounds

If Overdub mispronounces a word, try a different (incorrect, but phonetic) spelling. Once you’ve got it sounding right, you can always convert the Overdub to audio (see “Convert to audio” above) to correct the spelling in the transcript.

Ready to try a realistic voice generator for yourself?

Download Descript today and try Overdub for yourself. We have a feeling you’ll be impressed.

Featured articles:

No items found.

Articles you might find interesting

How They Made It

John August and Drew Marquardt on lessons learned after 10+ years of Scriptnotes

Scriptnotes is a titan in independent podcasting and a shibboleth among aspiring writers. Host John August and producer Drew Marquardt sat down with us to talk about their process.

Podcasting

Adding transition music to a podcast? Everything you need to know

Background music can add to the listening experience too, creating a sense of whatever emotion you want to evoke, but, you should know that you’ll likely have to pay for it.

Product Updates

Descript is Now SOC 2 Type I Compliant

Since Descript was founded, we’ve treated the security, confidentiality, and privacy of our users’ data with the utmost care. We know that the data our users share with us ranges from the personal to the proprietary, and we take our responsibility to protect that data very seriously.

Video

Video post-production: Tips to master video editing

Video post-production is where raw footage turns into magic. Learn the stages of post-production, from color correction to audio editing to motion graphics.

Related articles:

Share this article

Get started for free →