Notice: Act-Two significantly expands on Lip Sync's capabilities. Click here to learn more about the latest model. Act-Two requires a driving performance video, so Lip Sync may be useful in cases requiring text to speech or audio-driven generations.

Custom voices allows you to use your own voice with Text to Speech, letting you generate clips of your trained voice speaking any text you input. Each custom voice costs 300 credits to train.

Creating a custom voice

1. Select Record audio in the Generative Audio prompt box, then click Try it now.
2. Upload a voice sample between 2 to 5 minutes in length. The sample must be of your voice or someone whose voice you have explicit permission to clone. Ensure your recording has a good range of voice and tone, and reduce background noise as much as possible.
3. If you don't have a pre-recorded voice sample to upload, click View example for a script that you can record directly in the app.
4. Click Record Consent to proceed, and complete voice verification.
5. Give your voice a name for easy identification and click Submit. 

Using your cloned voice

Input any text into the Generative Audio prompt box, then click on your custom voice to select it. 

To view all your custom voices, you can click the Custom tab under the Voice menu. Hover over the name of your custom voice to delete, rename, or share it.