> For the complete documentation index, see [llms.txt](https://docs.agenticflow.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.agenticflow.ai/reference/nodes/elevenlabs_group_voices.md).

# ElevenLabs: Manage Voices

Find, design, clone, and manage voices and voice samples, including professional voice-cloning tasks.

Find this node under **ElevenLabs** in the action picker. It uses an [ElevenLabs connection](/integrations/connection-providers/media/elevenlabs.md).

## Set up the node

1. Add **ElevenLabs: Manage Voices** to your workflow.
2. Select your ElevenLabs connection.
3. Choose **Model / Action**. The configuration form changes to match your choice.
4. Fill the required fields, using values from earlier steps where needed.
5. Save your changes and run the step. Review its result in **Build** or **History**.

## Parameters and inputs

The fields depend on the selected action. Use the labels, required markers, and available choices shown in your form.

| Input                        | What to provide                                                                                |
| ---------------------------- | ---------------------------------------------------------------------------------------------- |
| Model / Action               | Choose a list, preview, design, cloning, settings, or voice-management action.                 |
| Voice description or samples | Describe a new voice, or supply the samples and details required by the chosen cloning action. |
| Existing voice or sample     | Choose the voice or sample to inspect, update, or remove.                                      |

See [model-specific forms](/workflows/media-action-forms.md) for dropdowns, media uploads, repeatable lists, and using earlier results.

## Outputs

Voice choices, previews, voice or sample details, settings, or training and verification status.

Use voices and samples you have permission to use. Professional cloning can require provider verification before training or use.

## Example

Choose **List Voices**, review the available voices, then use one of them in **Speech and Transcription**.

<details>

<summary>Available Model / Action choices</summary>

* Delete Sample
* Get Audio From Sample
* Create A New Voice From Voice Preview
* Design A Voice
* Remix A Voice
* Text To Voice Preview Streaming
* Get Default Voice Settings
* Get Voice Settings
* Edit Voice Settings
* Get Voice Accents
* List Voices
* Get Voice
* Delete Voice
* Edit Voice
* Get Voices V2
* Replicate Voice To Isolated Environment
* Add Voice
* Add Shared Voice
* Get Similar Library Voices
* Get Voices
* Create Pvc Voice
* Edit Pvc Voice
* Add Samples To Pvc Voice
* Update Pvc Voice Sample
* Delete Pvc Voice Sample
* Retrieve Voice Sample Audio
* Retrieve Voice Sample Visual Waveform
* Retrieve Speaker Separation Status
* Start Speaker Separation
* Retrieve Separated Speaker Audio
* Get Pvc Voice Captcha
* Verify Pvc Voice Captcha
* Run Pvc Training
* Request Manual Verification

</details>

Availability of individual models and resources depends on your provider account. A successful connection does not grant access to every action.

## Related guides

* [ElevenLabs connection and action overview](/integrations/connection-providers/media/elevenlabs.md)
* [Test a step and reuse earlier results](/workflows/workflow-single-run/run-step.md)
* [Retrieve media and save it to AI Drive](/workflows/workflow-single-run/media-results.md)