Give a character a voice

tendre.AI can make a character speak in a specific voice by learning it from a short audio sample, then lip-syncing the video so the line reads naturally on screen. Everything runs on your own GPU.

1. Open the Voice panel

With a clip or character selected, open the Voice tool from the generation panel.

2. Import a voice sample

Drop in a short, clean recording of the voice you want to use. A few seconds of clear speech with little background noise gives the steadiest result.

3. Write the line

Type the sentence or dialogue the character should say. Keep individual lines a natural length; split long dialogue into several clips rather than one very long line.

4. Generate and check the sync

Generate the clip and preview it. tendre.AI matches the mouth movement to the generated audio, so the line lands in sync with the face on screen.

To reuse the same voice across many clips without re-importing the sample each time, train a Sound LoRA. To layer effects or ambience around the dialogue, see Sound effects.