Files
AutoGPT/docs/integrations/block-integrations/talking_head.md
Nicholas Tindle 90466908a8 refactor(docs): restructure platform docs for GitBook and remove MkDo… (#11825)
<!-- Clearly explain the need for these changes: -->
we met some reality when merging into the docs site but this fixes it
### Changes 🏗️
updates paths, adds some guides
<!-- Concisely describe all of the changes made in this pull request:
-->
update to match reality
### Checklist 📋

#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
  <!-- Put your test plan here: -->
  - [x] deploy it and validate

<!-- CURSOR_SUMMARY -->
---

> [!NOTE]
> Aligns block integrations documentation with GitBook.
> 
> - Changes generator default output to
`docs/integrations/block-integrations` and writes overview `README.md`
and `SUMMARY.md` at `docs/integrations/`
> - Adds GitBook frontmatter and hint syntax to overview; prefixes block
links with `block-integrations/`
> - Introduces `generate_summary_md` to build GitBook navigation
(including optional `guides/`)
> - Preserves per-block manual sections and adds optional `extras` +
file-level `additional_content`
> - Updates sync checker to validate parent `README.md` and `SUMMARY.md`
> - Rewrites `docs/integrations/README.md` with GitBook frontmatter and
updated links; adds `docs/integrations/SUMMARY.md`
> - Adds new guides: `guides/llm-providers.md`,
`guides/voice-providers.md`
> 
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
fdb7ff8111. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: bobby.gaffin <bobby.gaffin@agpt.co>
2026-01-23 06:18:16 +00:00

1.8 KiB

Create Talking Avatar Video

What it is

This block is an AI-powered tool that creates video clips featuring a talking avatar using the D-ID service.

What it does

It generates a video of a digital avatar speaking a given script, with customizable voice, presenter, and visual settings.

How it works

The block sends a request to the D-ID API with your specified parameters. It then regularly checks the status of the video creation process until it's complete or an error occurs.

Inputs

Input Description
API Key Your D-ID API key for authentication
Script Input The text you want the avatar to speak
Provider The voice provider to use (options: microsoft, elevenlabs, amazon)
Voice ID The specific voice to use for the avatar
Presenter ID The visual appearance of the avatar
Driver ID The animation style for the avatar
Result Format The file format of the final video (options: mp4, gif, wav)
Crop Type How the video should be cropped (options: wide, square, vertical)
Subtitles Whether to include subtitles in the video
SSML Whether the input script uses Speech Synthesis Markup Language
Max Polling Attempts Maximum number of times to check for video completion
Polling Interval Time to wait between each status check (in seconds)

Outputs

Output Description
Video URL The web address where you can access the completed video
Error A message explaining what went wrong if the video creation failed

Possible use case

A marketing team could use this block to create engaging video content for social media. They could input a script promoting a new product, select a friendly-looking avatar, and generate a video that explains the product's features in an appealing way.