Your VSL says each viewer’s name
Chosen moments are voiced at watch time with the viewer’s own details, through your own ElevenLabs voice.
- Voiced
- At watch time
- Personal details
- Name, city, quiz answers
- Voice
- Your own ElevenLabs voice
- Key
- Bring your own
- Generation
- Handled by the player
Your script, their details, your voice
Built for quiz funnels: the answers ride in and come back out as spoken words.
Mark the moments
Pick the seconds where the video should speak to the viewer directly, and write the line with variables.
Voiced at watch time
Name, city, quiz answers: the viewer’s own details are synthesized into the audio as they watch.
Your voice, your key
Bring your own ElevenLabs voice and key. The player handles generation and playback.
Your quiz knows them. So should the video.
Answers ride in as custom data and come back out as spoken words.
The whole player, on every plan
Questions about AI Voice Segments
What gets personalized?
Only the moments you choose. You pick the seconds and write the line with variables such as name, city or quiz answers.
Where do the viewer’s details come from?
From data your page hands the player, such as quiz answers set in window.trackplay_data.
Which voice is used?
Your own. You bring your ElevenLabs voice and key, and the player handles generation and playback at watch time.
Can I see if personalization helps?
Yes. Custom data becomes a dimension, so you can compare retention by segment.