> For the complete documentation index, see [llms.txt](https://agpt.co/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://agpt.co/docs/integrations/block-integrations/narration.md).

# Video Narration

This block generates AI voiceover narration using ElevenLabs and adds it to a video, with flexible audio mixing options.

## Video Narration

### What it is

Generate AI narration and add to video

### How it works

The block uses ElevenLabs text-to-speech API to generate natural-sounding narration from your script. It then combines the narration with the video using MoviePy. Three audio mixing modes are available: **replace** (completely replaces original audio), **mix** (blends narration with original audio at configurable volumes), and **ducking** (similar to mix but applies stronger attenuation to original audio, making narration more prominent). The block outputs both the final video and the generated audio file separately.

### Inputs

| Input             | Description                                                                            | Type                                                                                                  | Required |
| ----------------- | -------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------- | -------- |
| video\_in         | Input video (URL, data URI, or local path)                                             | str (file)                                                                                            | Yes      |
| script            | Narration script text                                                                  | str                                                                                                   | Yes      |
| voice\_id         | ElevenLabs voice ID                                                                    | str                                                                                                   | No       |
| model\_id         | ElevenLabs TTS model                                                                   | "eleven\_multilingual\_v2" \| "eleven\_flash\_v2\_5" \| "eleven\_turbo\_v2\_5" \| "eleven\_turbo\_v2" | No       |
| mix\_mode         | How to combine with original audio. 'ducking' applies stronger attenuation than 'mix'. | "replace" \| "mix" \| "ducking"                                                                       | No       |
| narration\_volume | Narration volume (0.0 to 2.0)                                                          | float                                                                                                 | No       |
| original\_volume  | Original audio volume when mixing (0.0 to 1.0)                                         | float                                                                                                 | No       |

### Outputs

| Output      | Description                             | Type       |
| ----------- | --------------------------------------- | ---------- |
| error       | Error message if the operation failed   | str        |
| video\_out  | Video with narration (path or data URI) | str (file) |
| audio\_file | Generated audio file (path or data URI) | str (file) |

### Possible use case

* Adding professional voiceover to product demos or tutorials
* Creating narrated explainer videos from screen recordings
* Generating multi-language versions of video content
* Adding commentary to gameplay or walkthrough videos

***


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://agpt.co/docs/integrations/block-integrations/narration.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.