Skip to main content
When designing a voice agent experience, the voice that you choose plays a critical role in making the agent experience pleasant, natural, and understandable for your users. Cartesia offers 500+ voices out-out-of-box, as well as the ability to clone your own voices. Featured voices are a handpicked set of Voices that our Voices team believes to be great voices. We make this determination through a combination of usage, performance, robust internal evaluations, and customer feedback. These voices are a great starting point to find the best voice for your voice agent. Featured Voices are displayed with a check mark icon next to their names on our Voice Library page.

Stable voices (best for voice agents)

For voice agents in production, we’ve found that more stable, realistic voices perform better than studio quality, emotive voices. From our testing, we think these are the top performing English Voices for voice agents:
  • Male: Archie, Ronald, Carson, Jameson, Daniel
  • Female: Skylar, Gemma, Katie, Jacqueline, Cathy, Caroline

Emotive voices (best for AI characters)

Sonic is expressive with some voices like Tessa and Maya labeled as emotive in the playground, and respond well to emotion instructions. If your use case requires more expressive speech (e.g. companion apps, game characters), then we suggest trying:
  • Male: Kyle, Cory, Nolan
  • Female: Tessa, Ariana, Lucy
We tag such voices as Emotive in our playground and you can see a full list here. If you have your own audio recordings for AI characters or emotive voices, we would suggest using our Professional Voice Cloning feature to train a model specific to them.

Creating a Voice

If you can’t find a voice that suits your needs, you can easily create your own custom voices. This can be done from audio samples or from a base voice. We offer two methods of creating voices - Instant Clones and Professional Voice Clones.

Sharing a voice

Voices you create are private to your Cartesia organization by default. To use a custom voice on a third-party platform, share the voice first.
  • In the dashboard: open the My Voices tab, use the three-dots menu next to a voice, and select Share.
  • Via the API: call the Update Voice API and set access.type to public. Set it back to private to stop sharing.
To see which voices are currently shared, call the List Voices API with is_owner=true and look for voices with access.type set to public.