### Answer Yes, when you clone a voice using the Clone Voice API, the response includes a

preview_audio_url

field. [(1) ]() This URL points to a preview audio file of the cloned voice that you can use to listen to how it sounds. Example response structure:

json
{
  "voice_id": "11labs-Adrian",
  "voice_name": "Adrian",
  "provider": "elevenlabs",
  "gender": "male",
  "accent": "American",
  "age": "Young",
  "preview_audio_url": "<https://retell-utils-public.s3.us-west-2.amazonaws.com/adrian.mp3%22>
}

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

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

### Answer Based on the available sources, the Clone Voice API does not include a parameter to specify custom text for generating a preview audio. [(1) ]() The

preview_audio_url

returned in the response is automatically generated by the system—there's no documented option to customize what text is spoken in that preview. If you need to hear your cloned voice speak specific text, you would need to: 1. Clone the voice to get the

voice_id

2. Create a voice agent using that

voice_id

[(2) ]() 3. Test the agent with your desired text through a call or the dashboard Check out these potentially useful sources for more details: - [Clone Voice]() - [Create Voice Agent]() - [Get Voice]() Would you like a general answer based on my knowledge, or do you have other questions about working with cloned voices?

​ To learn more, see the sources I considered: [[1] Clone Voice](https://docs.retellai.com/api-references/clone-voice) [[2] Create Voice Agent](https://docs.retellai.com/api-references/create-agent) ​

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

### Answer Based on the available sources, Retell AI does not appear to offer a standalone Text-to-Speech (TTS) API endpoint for generating audio from arbitrary text. Retell AI's TTS capabilities are integrated within the voice agent pipeline—TTS is used to convert the LLM's response into speech during live calls. [(1) ]() If you want to hear a specific voice speak custom text, your options include: - Creating a voice agent with your cloned

voice_id

and testing it through a call or the dashboard , [(2) ]() - Using the voice agent in a test call scenario where you can control what the agent says For a dedicated TTS API that lets you input text and receive audio output directly, you may need to use the underlying TTS provider (such as ElevenLabs, Cartesia, or Minimax) directly through their own APIs. Check out these potentially useful sources: - [Clone Voice]() - [Create Voice Agent]() Would you like me to try to answer generally based on my knowledge?

​ To learn more, see the sources I considered: [[1] Create Voice Agent](https://docs.retellai.com/api-references/create-agent) [[2] Clone Voice](https://docs.retellai.com/api-references/clone-voice) ​

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