AI Voiceover Customization Controls
Customize AI voiceovers in Biteable using advanced controls to create personalized, dynamic narration for your videos. This guide shows you how to fine-tune your voiceovers.
Common Questions:
How do I add a pause in my voiceover?
How do I control the speed of my voiceover?
Biteable uses Amazon for AI voices. Amazon voices support SSML for modifying voices. Not all voices are supported for their full set of SSML controls, but we have provided information on how you can make certain adjustments to voices in this guide below.
If you apply a voice customization control in your voiceover and receive an error, or do not hear the effect in the final output, the voice you have chosen may not be supported for that type of customization. Please choose a different voice and try again or reach out to support for assistance.
Add a pause in a voiceover.
Default pause: <break/>
Time specific pause: <break time="2s"/>
Hi there. Welcome to Biteable. <break/> Let’s take a 2 seconds deep breath before we get started. <break time="2s"/> Ok. That was nice.
Adjust the speed or volume of the speaker in a voiceover.
Adjust Speed: <prosody rate="slow">TEXT</prosody>
Speed Options: x-slow, slow, medium, fast,`x-fast`. Sets the speaking rate to a predefined value for the selected voice.
Hi there. I'll count up to five fast, then down slowly, <prosody rate="x-slow"> one two three four five </prosody> <prosody rate="x-fast"> five four three two one </prosody> How was that?
Adjust Volume: <prosody volume="loud">TEXT</prosody>
Volume Options: silent, x-soft, soft, medium, loud, x-loud: Sets the volume to a predefined value for the current voice.
This is what voices sound like at a normal volume. <prosody volume="x-loud"> This is what voices sound like at extra loud volume </prosody> <prosody volume="x-soft"> This is what voices sound like at extra soft volume </prosody>
There are four different types of voices we use for AI voices.
Generative: Produces the most expressive and adaptive speech using Generative AI.
Long-Form: Produces the most natural sounding speech for longer content.
Neural: Produces more natural and human-like speech than Standard Engine.
Standard: Produces natural-sounding speech.
Advanced SSML controls are not available for all voice types. Below are the names of Biteable voices, the type of voice they use, and the advanced SSML controls available for each voice.
Becky (Long-Form): Pause, Speed, Volume
Ruth (Generative): Pause
Chelsea (Neural): Pause, Speed, Volume
Salli (Neural): Pause, Speed, Volume
Gibson (Generative): Pause
Stephen (Generative): Pause
Matthew (Neural): Pause, Speed, Volume
Joelle (Long-Form): Pause, Speed, Volume
Danielle (Neural): Pause, Speed, Volume
Joanna (Generative): Pause
Gregory (Neural): Pause, Speed, Volume
Willow (Generative): Pause
Amy (Neural): Pause, Speed, Volume
Arthur (Neural): Pause, Speed, Volume
Emma (Neural): Pause, Speed, Volume
Brian (Neural): Pause, Speed, Volume
Leah (Generative): Pause, Speed, Volume
Common Questions:
How do I add a pause in my voiceover?
How do I control the speed of my voiceover?
Biteable uses Amazon for AI voices. Amazon voices support SSML for modifying voices. Not all voices are supported for their full set of SSML controls, but we have provided information on how you can make certain adjustments to voices in this guide below.
If you apply a voice customization control in your voiceover and receive an error, or do not hear the effect in the final output, the voice you have chosen may not be supported for that type of customization. Please choose a different voice and try again or reach out to support for assistance.
Add a Pause
Add a pause in a voiceover.
Syntax
Default pause: <break/>
Time specific pause: <break time="2s"/>
Example
Hi there. Welcome to Biteable. <break/> Let’s take a 2 seconds deep breath before we get started. <break time="2s"/> Ok. That was nice.
Adjust Speed and Volume
Adjust the speed or volume of the speaker in a voiceover.
Syntax
Speed
Adjust Speed: <prosody rate="slow">TEXT</prosody>
Speed Options: x-slow, slow, medium, fast,`x-fast`. Sets the speaking rate to a predefined value for the selected voice.
Example
Hi there. I'll count up to five fast, then down slowly, <prosody rate="x-slow"> one two three four five </prosody> <prosody rate="x-fast"> five four three two one </prosody> How was that?
Volume
Adjust Volume: <prosody volume="loud">TEXT</prosody>
Volume Options: silent, x-soft, soft, medium, loud, x-loud: Sets the volume to a predefined value for the current voice.
Example
This is what voices sound like at a normal volume. <prosody volume="x-loud"> This is what voices sound like at extra loud volume </prosody> <prosody volume="x-soft"> This is what voices sound like at extra soft volume </prosody>
Supported Voices & Controls
There are four different types of voices we use for AI voices.
Generative: Produces the most expressive and adaptive speech using Generative AI.
Long-Form: Produces the most natural sounding speech for longer content.
Neural: Produces more natural and human-like speech than Standard Engine.
Standard: Produces natural-sounding speech.
Advanced SSML controls are not available for all voice types. Below are the names of Biteable voices, the type of voice they use, and the advanced SSML controls available for each voice.
Becky (Long-Form): Pause, Speed, Volume
Ruth (Generative): Pause
Chelsea (Neural): Pause, Speed, Volume
Salli (Neural): Pause, Speed, Volume
Gibson (Generative): Pause
Stephen (Generative): Pause
Matthew (Neural): Pause, Speed, Volume
Joelle (Long-Form): Pause, Speed, Volume
Danielle (Neural): Pause, Speed, Volume
Joanna (Generative): Pause
Gregory (Neural): Pause, Speed, Volume
Willow (Generative): Pause
Amy (Neural): Pause, Speed, Volume
Arthur (Neural): Pause, Speed, Volume
Emma (Neural): Pause, Speed, Volume
Brian (Neural): Pause, Speed, Volume
Leah (Generative): Pause, Speed, Volume
Updated on: 08/01/2025
Thank you!