### Answer To clone a voice using the SDK, you need to pass the files as an array of file streams using

fs.createReadStream()

. Here's the documented approach:

javascript
import Retell from 'retell-sdk';
const client = new Retell({
 apiKey: 'YOUR_RETELL_API_KEY',
}) ;
const voiceResponse = await client.voice.clone({
 files: [fs.createReadStream('path/to/file') ],
 voice_name: 'x',
}) ;
console.log(voiceResponse.provider) ;

[(1) ]() Key details: - The

files

parameter expects an array of file streams created with

fs.createReadStream()

- You can upload up to 25 files for ElevenLabs, but only 1 file is supported for Cartesia and MiniMax - You can optionally specify a

voice_provider

(defaults to

elevenlabs

) , with available options:

elevenlabs

,

cartesia

,

minimax

If you're receiving an HTML-based internal server error, a few things to check: - Ensure you're using

fs.createReadStream()

with a valid file path (not a ReadableStream from another source) - Verify your API key is correctly set in the Authorization header - Confirm the audio file format is compatible with the voice provider you're using The documentation doesn't specify exact audio format requirements, so if issues persist, I'd recommend reaching out via: - Visit [Documentation]() - Visit [Hire certified Retell partner]()

​ 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 Yes,

fs.createReadStream('path/to/file')

expects the local file path on your system where the audio file is stored. [(1) ]() For example, if your audio file is located at

/Users/yourname/audio/voice-sample.mp3

, you would use:

javascript
files: [fs.createReadStream('/Users/yourname/audio/voice-sample.mp3') ]

The

fs

module is Node.js's built-in file system module, and

createReadStream

reads the file from your local disk and streams it to the API.

​ 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 --- When using the Retell SDK, you don't need to manually set headers—the SDK handles authorization automatically when you initialize the client with your API key. [(1) ]()

javascript
import Retell from 'retell-sdk';
const client = new Retell({
  apiKey: 'YOUR_RETELL_API_KEY',
}) ;

[(2) ]() The

apiKey

you provide during client initialization is automatically included as the

Authorization

header (in the format

Bearer YOUR_API_KEY

) for all subsequent API calls, including the

client.voice.clone()

method. So your complete clone voice call would simply be:

javascript
import Retell from 'retell-sdk';
const client = new Retell({
  apiKey: 'YOUR_RETELL_API_KEY',
}) ;
const voiceResponse = await client.voice.clone({
  files: [fs.createReadStream('path/to/file') ],
  voice_name: 'x',
}) ;
console.log(voiceResponse.provider) ;

No additional header configuration is needed when using the SDK—that's one of its main benefits over using the REST API directly. [(1) ]()

​ To learn more, see the sources I considered: [[1] SDKs](https://docs.retellai.com/get-started/sdk) [[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.