### Answer Yes, the provider you choose when using the Clone Voice API does matter. [(1) ]() When calling the Clone Voice API, you must specify a

voice_provider

parameter. The available options are: -

elevenlabs

-

cartesia

-

minimax

-

fish_audio

-

platform

Each provider has different capabilities and constraints: - **Cartesia and MiniMax**: Only support 1 audio file for cloning - **Inworld**: Supports up to 3 audio files - **ElevenLabs and others**: Support up to 25 audio files If you set

voice_provider

to

platform

, the cloned voice will behave as a platform voice with automatic TTS fallback handling, meaning you won't need to configure TTS fallback separately. [(2) ]() The provider choice affects the quality, characteristics, and behavior of your cloned voice, so select based on your specific requirements and the number of audio samples you have available.

​ To learn more, see the sources I considered: [[1] Clone Voice](https://docs.retellai.com/api-references/clone-voice) [[2] Platform voices](https://docs.retellai.com/build/platform-voices) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

@AI Evy does it cost money?

### Answer I don't have specific pricing information for voice cloning in the available sources. However, I can share that Retell AI's general pricing model is pay-as-you-go with a flat fee of $0.07+/minute for AI voice agents. [(1) ]() The platform also provides 60 minutes of complimentary access for new users. For detailed pricing on voice cloning specifically, I recommend checking Retell AI's pricing page or contacting their team directly.

​ To learn more, see the sources I considered: [[1] Bland AI Review: Real Costs, Latency Issues & Better Option | Retell AI](https://www.retellai.com/blog/bland-ai-reviews) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.