I do not use my own voice or video. Please add the option to add a TTS track using AI voice like Clipchamp does. Maybe enable 11labs or use the quite good Microsoft voices.
Thanks for a great product, we’re rapidly producing our help center videos with flair now.
My workflow is:
Plan out my demo, use the teleprompter for steps.
Set up the video environment, browser in fullscreen, close all other apps and turn on “Do not disturb” in windows 11 (maybe this can be done automatically or already is?)
Start recording, moving the mouse slowly, pausing on clicks (maybe also a feature request) and following the script along.
Finish recording leaving a short pause that I can edit out to time the end dialogue.
Add spotlight and zoom, love how easy it is on the timeline, this is ideally where the TTS blocks would live if implemented. I am using our template which is awesomely loading automatically saving me time in settings!
Export to 16:9, 60 fps
Import to Clipchamp, would use Final Cut but the TTS option is gold.
Add intro with animating company name zoom and welcome speech, add transitions, add music, add perfectly timed TTS and outro with logo and background.
Review and export an publish to help center
The reason we are using TTS/Clipchamp is that:
Anyone can take over the video job - we have the brand voice locked in (maybe a option to sample ones own voice or use one of yours)
Consistency in the voice, no sore throat or recording environment to take care off.
We do not use a video avatar or ourselves in the video.
I can focus on just doing the video.
We are in several markets so it’s easy to change language of the TTS. (would be insanely awesome if you could batch export in different languages)
Timing is super easy, I can add TTS blocks exactly timed to the screen action.
I can control the speed of the TTS voice, setting it to 1.2 speed gives the video a fast paced fresh vibe.
I can add … ! ? , for different voice effects (would be great to have the same method gesture control you have for Avatars but for voice.)
I can control the pitch of the voice.
I can add the intro and nice slow zoom logo animation.
I can publish to Microsoft Streams directly for internal review
I can add music.
FocuSee Product Team
Team•
Dec 19, 2025
Thank you very much for your feature suggestion. We have recorded your feedback in our system and will carefully evaluate it in future product iterations.
We would also like to better understand why you prefer AI-generated audio over your original recordings. Knowing your use cases and considerations will help us improve the product experience.
Thank you for your support of FocuSee, and we look forward to receiving more valuable feedback from you.
This request was merged into another request
Comments2
bla@vitus.cloud
Dec 19, 2025
Hello Team!
Thanks for a great product, we’re rapidly producing our help center videos with flair now.
My workflow is:
Plan out my demo, use the teleprompter for steps.
Set up the video environment, browser in fullscreen, close all other apps and turn on “Do not disturb” in windows 11 (maybe this can be done automatically or already is?)
Start recording, moving the mouse slowly, pausing on clicks (maybe also a feature request) and following the script along.
Finish recording leaving a short pause that I can edit out to time the end dialogue.
Add spotlight and zoom, love how easy it is on the timeline, this is ideally where the TTS blocks would live if implemented. I am using our template which is awesomely loading automatically saving me time in settings!
Export to 16:9, 60 fps
Import to Clipchamp, would use Final Cut but the TTS option is gold.
Add intro with animating company name zoom and welcome speech, add transitions, add music, add perfectly timed TTS and outro with logo and background.
Review and export an publish to help center
The reason we are using TTS/Clipchamp is that:
Anyone can take over the video job - we have the brand voice locked in (maybe a option to sample ones own voice or use one of yours)
Consistency in the voice, no sore throat or recording environment to take care off.
We do not use a video avatar or ourselves in the video.
I can focus on just doing the video.
We are in several markets so it’s easy to change language of the TTS. (would be insanely awesome if you could batch export in different languages)
Timing is super easy, I can add TTS blocks exactly timed to the screen action.
I can control the speed of the TTS voice, setting it to 1.2 speed gives the video a fast paced fresh vibe.
I can add … ! ? , for different voice effects (would be great to have the same method gesture control you have for Avatars but for voice.)
I can control the pitch of the voice.
I can add the intro and nice slow zoom logo animation.
I can publish to Microsoft Streams directly for internal review
I can add music.
FocuSee Product Team
Dec 19, 2025
Thank you very much for your feature suggestion. We have recorded your feedback in our system and will carefully evaluate it in future product iterations.
We would also like to better understand why you prefer AI-generated audio over your original recordings. Knowing your use cases and considerations will help us improve the product experience.
Thank you for your support of FocuSee, and we look forward to receiving more valuable feedback from you.