How to use voice mirroring

Voice Mirroring gives you full creative control over how your avatar sounds by letting it perform using your own vocal delivery. Instead of relying on standard text-to-speech, you record your own audio, your natural tone, rhythm, and pacing, HeyGen mirrors it through your selected avatar and voice. The result feels authentic, expressive, and true to your style.

Start with a new or existing project

Create a new video or open an existing project. Add a new scene and choose your avatar.

In the script editor, click Audio. From here, you can either record new audio or upload an existing file. For this walkthrough, choose Record Audio.

Record your delivery

When recording, speak with the tone, pacing, and emotion you want your avatar to match. Once the recording is complete, preview it and re-record if needed.

When you’re satisfied, enable Voice Mirroring and click Add Audio. HeyGen will automatically transcribe your audio, display the text in the scene, and allow you to review it for accuracy.

Apply your delivery to a voice

Next, select the voice you want to use. Your recorded delivery, including tone, pacing, and emotion, will be mirrored onto the selected voice.

Use Voice Mirroring in an existing scene

If you start with a text-only script and the delivery doesn’t sound quite right, you can refine it using Voice Mirroring.

Click the three-dot menu next to your script and select Convert to Voice Mirroring. Your script will appear like a teleprompter, allowing you to record or upload audio with the delivery you want.

Once recorded, the new audio is added to the scene automatically.

Edit or revert your audio

You can turn your recording into a custom voice clone if needed. If you want to revert back to text, select Turn Audio into Text, or choose Delete Audio to remove the recording entirely.