Sound is half the impression a video makes. In Telematic, voiceover, subtitles and music are configured once in a preset and then work automatically.
Voices
The library offers realistic neural voices for different languages. The voice is chosen in the video preset; there you can also set the voice character β a free-form description of the delivery ("calm narrator", "energetic host") that shapes the performance β and the speech rate.
Before voicing, the text goes through automatic preparation: numbers and abbreviations are expanded into words ("$1,500" becomes "one thousand five hundred dollars") so the synthesis doesn't stumble. The voiceover language is pinned to the project's content language β the voice won't "flip" to another language because of foreign words in the text.
Your own voiceover
You can voice any scene yourself:
- record or prepare the audio and upload the file to the scene β it's free, and no synthesis is run for that scene;
- or open the built-in audio editor: waveform view, microphone recording, basic processing and undo β all in the browser, no extra software.
Subtitles keep working either way: the system transcribes your recording itself and aligns the text to the timing.
Subtitles
Subtitles are generated automatically and synced to the audio word by word. You can configure the style and the position in the frame: simply drag and resize the subtitle box in the preview β for example, lift it above the Shorts interface overlay. The position is saved in the preset.
Music and volume levels
The preset defines background music and separate volume levels: voice and music are adjusted independently. For YouTube, automatic loudness normalization to the platform standard (β14 LUFS) is applied β your videos sound consistently loud and don't "sink" next to others.
Cost
Voiceover is billed by duration: 1 token per 6 seconds of finished speech. Uploading your own voiceover is free. The full cost breakdown of a video is in "Tokens and Billing".