Skip to main content
If you find the existing voice doesn’t meet your needs, you can add a custom voice. There’s a limit of 100 custom voices per account. If you need more, please contact us via the Customer Support Portal or support@retellai.com.
Start with Platform Voices — Retell’s built-in voices with automatic TTS fallback. Add a custom voice only if none of them fit.

Add Custom Voice

Open the voice selector, go to Custom Providers, pick a provider (MiniMax, Cartesia, Fish Audio, Inworld, or ElevenLabs), then click Add custom voice. On the Community Voices tab, search by voice name or voice ID to add a publicly available community voice.
Add Custom Voice dialog on the Community Voices tab for ElevenLabs, with a Voice Name search field

Add Voice Clone

The recommended way to clone a voice is from the Platform Voices tab: click Add voice clone, which creates a platform voice clone (automatic TTS fallback, same as built-in platform voices). You can also train a clone through a custom provider’s Voice Clone tab using the steps below.
1

Open Add custom voice

Open the voice selector, select Custom Providers, choose your provider, then click Add custom voice.
Select Voice dialog on the Custom Providers tab showing MiniMax, Cartesia, Fish Audio, Inworld, and ElevenLabs, with the Add custom voice button
2

Train Your Voice Clone

Open the Voice Clone tab, enter a voice name, upload your audio clip, confirm the consent checkbox, then click Save.
Add Custom Voice dialog on the Voice Clone tab for ElevenLabs, with Voice Name, upload audio clip, and consent checkbox

What to say in the recordings

Cloning captures how the voice sounds, not what it says, so you don’t need to read a specific script. Any natural speech works. For the best result:
  • Speak in the tone, pace, and energy you want the agent to use on calls. The clone reproduces the delivery it hears.
  • Use continuous, conversational speech rather than isolated words or long pauses.
  • Record a single speaker with no background noise, music, or echo.
  • Avoid heavily edited or compressed audio. A clean microphone recording works better than audio captured from a phone or video call.

File limits

File limits depend on the voice provider you clone with. Inworld voice cloning accepts up to 3 files and 16 MB of audio in total, while Cartesia, MiniMax, and platform clones take a single file. ElevenLabs clones accept up to 25 files via the Clone Voice API. In the dashboard upload field, ElevenLabs accepts audio and video formats up to 10 MB per clip.