> For clean Markdown of any page, append `.md` to the page URL.
> For a complete documentation index, see https://docs.sarvam.ai/llms.txt.
> For full documentation content in one file, see https://docs.sarvam.ai/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server.

# Welcome to Sarvam Studio

<h2>
  One studio. Every Indian language.
</h2>

<p>
  Generate, clone, and localize audio and video - no code required.
</p>

<img src="https://files.buildwithfern.com/https://sarvam-api-docs.docs.buildwithfern.com/2a0c0c666e4014e9c0529d4a50d0a2488d847ea5b4b1dbe7fc82b987b675ce1b/sarvam-creative/images/home_page.png" alt="Sarvam Creative dashboard home screen, showing a Video Dubbing highlight and a Start creating grid with Video Dubbing, Voice Cloning, Speech to Text, and Text to Speech cards." />

Sarvam Studio is Sarvam AI's self-serve content production platform, built with deep native support for Indian languages. Sarvam Creative - the suite covered in this section - lets creators, educators, marketers, and developers generate, clone, and localize audio and video content directly from the dashboard, with no code and no dev team required. If you're validating a capability before you wire it into your own product via API, the dashboard is also where that starts.

### Sarvam Creative (Media Generation & Transformation)

A web-based studio to instantly generate, clone, and localize audio and video content.

Localize videos into Indian languages with speaker voice preservation.

Synthesize natural, human-like voices from a library of premium personas.

Browse Sarvam's curated voices and your own cloned personas in one place.

Map a speaker's unique vocal traits into a reusable persona in a few steps.

Transcribe audio across regional Indian dialects, with speaker diarization.

## Who It's For

Built for anyone whose work involves producing audio or video in more than one Indian language:

* **Content creators & marketers** - localizing videos, ads, and social content into multiple languages without hiring a studio or a voice artist per language.
* **Educators & course creators** - dubbing lecture content, narrating course material, and reaching students across language barriers.
* **Podcasters & storytellers** - narrating scripts and voicing content with Text to Speech and a consistent Voice Library persona.
* **Developers** - proving out a capability on the dashboard first, then wiring the same pipeline into their own product via the API.

Building something with these features programmatically? See the [API Reference](/api-reference-docs/getting-started) for endpoint-level docs.