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

> ## Agent Instructions
> Flowy is a node-based AI creative platform: you generate images, video, audio, 3D and vector on an infinite Canvas, refine on the Studio timeline, and export or publish from the same project.
> Prefer the Flowy MCP server (https://mcp.tryflowy.ai/mcp) or the REST API at https://apis.tryflowy.ai/v1 for programmatic work. Install with `flowy mcp install` from the @flowy/cli package.
> Credits are workspace-scoped. Generations reserve credits on start and only deduct on success, so failed runs refund automatically.

# Voiceover

> Turn a script into studio-quality speech, in the voice of your choice.

Voiceover reads a script aloud in a natural voice. Pick MiniMax, ElevenLabs, or Gemini, choose a voice, and download the take as an MP3.

<Frame>
  <img src="https://mintcdn.com/flamapp/F3HzOSEZ0flnKi-X/images/tools/voiceover.png?fit=max&auto=format&n=F3HzOSEZ0flnKi-X&q=85&s=ec0b02dbaff3913043428134b5e4097b" alt="Voiceover" width="2880" height="1800" data-path="images/tools/voiceover.png" />
</Frame>

## Where to find it

Open **/audio/voiceover** directly, press <kbd>⌘</kbd> <kbd>K</kbd> and search "Voiceover", or find it in the **Audio** area of the left sidebar.

## What you need

| Input  | Required | Notes                                                                                                                                                                |
| ------ | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Script | Yes      | The text to read aloud. Max length depends on the model: 10,000 characters on MiniMax, 5,000 on ElevenLabs, 50,000 on Gemini.                                        |
| Voice  | —        | The catalog is per model. MiniMax defaults to Wise Woman (one of 6 preset voices); ElevenLabs defaults to Rachel; Gemini defaults to Kore (one of 30 studio voices). |
| Model  | —        | 3 models. See below. Default: **MiniMax Speech 2.8 HD**.                                                                                                             |
| Speed  | —        | `0.5x`–`2x`, default `1x`. MiniMax only: hidden for ElevenLabs and Gemini.                                                                                           |

## Models

| Model                              | Provider   | Credits                | Notes                                                                                                     |
| ---------------------------------- | ---------- | ---------------------- | --------------------------------------------------------------------------------------------------------- |
| MiniMax Speech 2.8 HD: **default** | MiniMax    | 150 / 1,000 characters | Highest-fidelity preset voices. 6 voices in the panel, plus the speed slider.                             |
| ElevenLabs v3: *premium*           | ElevenLabs | 150 / 1,000 characters | Expressive, emotive delivery. Its own voice catalog; no speed control. Script capped at 5,000 characters. |
| Gemini Flash TTS                   | Gemini     | 225 / 1,000 characters | 30 studio voices, natural pacing. No speed control. Script capped at 50,000 characters.                   |

## What it costs

150 credits per 1,000 characters on MiniMax or ElevenLabs, 225 on Gemini, billed on script length, rounded up to the next 1,000 characters. Flowy shows a live estimate in the panel before you run. The backend's pricing is always authoritative.

## Related

* [Change Voice](/tools/change-voice)
* [Translation](/tools/translation)
* [Lipsync Studio](/tools/lipsync-studio)