> 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/kling_group_audio_generation.md).

# Kling: Generate Audio

Generate speech or sound from text, or create audio for a video.

Find this node under **Kling** in the action picker. It uses a [Kling connection](/integrations/connection-providers/media/kling.md).

## Set up the node

1. Add **Kling: Generate Audio** to your workflow.
2. Select your Kling 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 text-to-speech, text-to-audio, or video-to-audio.              |
| Text or video            | Provide narration text, a sound description, or a video as requested. |
| Voice and audio settings | Choose the voice and controls supported by the selected action.       |

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

## Outputs

Audio results or a task identifier and status, depending on the selected operation.

For a pending task, retrieve its existing result instead of running the generation step again.

## Example

Choose the text-to-audio action and describe a soft rain ambience. If it returns a task, use the matching text-to-audio query in **Get and List Tasks**.

<details>

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

* Video — Avatar — Text To Speech — Create Task
* Video — Audio Generation — Text To Audio — Create Task
* Video — Audio Generation — Video To Audio — Create Task

</details>

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

## Related guides

* [Kling connection and action overview](/integrations/connection-providers/media/kling.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)