> ## Documentation Index > Fetch the complete documentation index at: https://anam.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Custom Voices > Create a custom voice by cloning audio with Anam or importing a supported provider voice, then assign it to a persona. You can clone a voice directly in Anam Lab without writing code, import a voice from a supported provider, or create a voice through the API. ## Clone or upload a voice in Lab Sign in to [Anam Lab](https://lab.anam.ai) and open the persona you want to update. Your organization must have custom voice access enabled to clone or import a voice. If Lab reports an access error, contact [Anam Support](mailto:support@anam.ai) to check your organization's access. Select the **Voice** tab, then **Start recording**. This opens the cloning screen, which supports both recording and uploading audio. Record a sample using your microphone, or select **Upload audio file** to use an existing recording. You do not need to record a new sample to reach the upload option. For microphone recording, read the displayed script for 10–15 seconds. The recorder stops automatically at 15 seconds. Review your sample before continuing. Select **Continue**, enter a **Voice Name**, and choose the language and other voice details. Select **Clone & Preview**, then listen to the preview. Select **Use this voice** to assign the clone to your persona, then **Publish** to apply the change. ### Lab audio requirements * Upload WAV, MP3/MPEG, MP4/M4A, WebM, or OGG audio. * The file must be at least 10 KB and no larger than 50 MB (10,240–52,428,800 bytes). * The 15-second limit applies to the in-browser recorder, not to uploaded file duration. Uploaded files still need to pass file validation and the voice provider's processing checks. ## Import a provider voice in Lab Provider import is different from uploading an audio recording. Import public ElevenLabs library voices and shared Cartesia voices through **Voice > Import from provider** using the **Provider Voice ID**. For an ElevenLabs Professional Voice Clone, follow the sharing and Anam Support steps below rather than the self-service import path. ## Import ElevenLabs voices The import process depends on whether the voice is public or cloned. ### Public Voice Library voices If a voice appears in the public ElevenLabs Voice Library, copy its Voice ID and import it directly in the [Anam Lab](https://lab.anam.ai). ### Cloned voices Anam must import cloned voices and add them to your account before you can use them in Lab. Open the cloned voice, select **Voice sharing**, and switch to the **External & Voice Library** tab. Enable **External link sharing** and copy the share link. For the most reliable import, set the link access to **Anyone with the link**. ElevenLabs voice sharing dialog with the External & Voice Library tab selected and external link sharing enabled Email the share link to [support@anam.ai](mailto:support@anam.ai). Anam will import the voice, add it to your account, and confirm when it is available. Only the **Professional Voice Clone** voice type in ElevenLabs can be shared with external organisations. ## Import Cartesia voices Any localized or cloned Cartesia voice must be public before Anam can import it. Open the voice's sharing settings and select **Shared**. Cartesia describes this setting as **Anyone with the voice ID can use it**. Cartesia voice sharing dialog with Shared selected so anyone with the voice ID can use the voice Copy the Cartesia Voice ID, then import the voice in the [Anam Lab](https://lab.anam.ai). ## Create a voice with the API Use [create voice](/docs/api-reference/voices/create-voice) for programmatic cloning or provider import. The API supports audio sent as multipart form data, an uploaded audio reference, or a provider voice ID. For larger audio uploads, use [create voice presigned upload](/docs/api-reference/voices/create-voice-presigned-upload), upload the audio to the returned URL, then pass the returned `audioKey` to create voice. Follow the API reference's upload requirements rather than assuming the Lab file formats and limits apply to the API. ## Next Steps Browse available avatars to pair with your voice Learn more about configuring personas Write effective system prompts for multilingual personas Understand session token creation This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.