> ## Documentation Index
> Fetch the complete documentation index at: https://docs.decktalk.app/llms.txt
> Use this file to discover all available pages before exploring further.

# FAQ

> What DeckTalk costs with ElevenLabs, whether you are locked in, how it compares with Remotion, Motion Canvas, Manim, reveal.js, Descript, Synthesia, and HeyGen, and what it writes besides the video.

## What does it cost?

You need an ElevenLabs plan with API access. The free tier has the API, but its audio
carries a watermark and a non-commercial license, so the Starter plan is the practical
floor. A ten-minute narration is roughly 9,000 characters, which fits inside that plan's
monthly allowance several times over. Because DeckTalk caches sections by text, an edit
costs the sentences you changed rather than the whole script, and `decktalk narrate --dry-run`
prints exactly what a build would send before it sends it. Everything else is free.
Chromium and ffmpeg run on your machine, and `--silent` builds spend nothing.

## Is there lock-in to ElevenLabs?

ElevenLabs is the only speech provider today because it returns a timestamp for every
word. The provider is one module behind a two-method protocol, and anything that returns
word times can take its place. A local text-to-speech engine with a forced aligner is the
obvious candidate. The `--silent` flag needs no provider at all, so the project format
does not depend on any vendor. [Python API](/reference/python-api#speech-providers) has
the protocol.

## How does the voice sound?

Any ElevenLabs voice id works, including a clone of your own. Stability, similarity,
style, and speed are settings under `[voice]` in `decktalk.toml`. DeckTalk sends the
previous and next text with each section so that the prosody stays continuous across
cuts.

## Why not record the screen?

You would record it again after every edit, and you would re-time every reveal by hand.
Here an edit rebuilds one section, and the reveals follow the words wherever they move.

## How is this different from the other tools?

| Tool                        | Timing comes from                                | Slides are               | Cost of editing one sentence               |
| --------------------------- | ------------------------------------------------ | ------------------------ | ------------------------------------------ |
| **DeckTalk**                | the spoken words, one timestamp each             | your HTML                | one section re-synthesized and re-recorded |
| Remotion, Motion Canvas     | frame numbers or seconds in code                 | React or TypeScript code | you re-time by hand                        |
| Manim                       | seconds in a Python animation                    | Python scenes            | you re-time by hand and re-render          |
| reveal.js plus a TTS script | a fixed delay per slide, or a hand-made timeline | your HTML                | you re-time every slide after the change   |
| Descript                    | a recording you made                             | your screen              | you re-record the clip                     |
| Synthesia, HeyGen           | the avatar's speech                              | their templates          | you regenerate the video                   |

Remotion, Motion Canvas, and Manim are for animation, where the frame is the unit and
the narration is fitted afterwards. reveal.js with a text-to-speech track gets you
slides and a voice, but nothing ties a reveal to a word, so every edit means re-timing.
Descript edits a recording you already made. Synthesia and HeyGen put an avatar on
screen. DeckTalk is for the case where the timing should come from the words and the
slides are yours.

## Is generated music required?

No. The soundscape stays off until `[mix]` names a file, and you can bring your own
files. The `soundscape` command exists for when you want ElevenLabs to make the bed and
the effects from a prompt. [Sound](/concepts/sound) explains both.

## What comes out besides the video?

Every build writes captions as `.srt` and `.vtt` from the word timestamps, with the
script's punctuation, and an ffmetadata chapters file with one chapter per section, which
is also muxed into the mp4 so players show the section titles. `decktalk status` lists
all three. [Build artifacts](/reference/artifacts#buildout) has the formats.

## Does another HTML framework work?

Yes. A page is any HTML that honors the [page contract](/concepts/page-contract), and
[Write a page by hand](/guides/page-by-hand) shows the minimum. The runtime is one file
with no dependencies, and it adds nothing to your markup beyond the stage element. KaTeX
is optional, and `init` vendors it into the project.

## Does it run on Windows?

Yes. The test suite and a full offline build run on Linux, macOS, and Windows in CI for
every push to `main`.

## Where does the name come from?

A deck is the slides. The talk is the narration. DeckTalk cuts the one to the other.