> 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. # Creating a Dub Create a new dub in two steps - upload your source file, then add your dubbing details - and track it through processing. For an overview of what Dubbing does and who it's for, see the [Dubbing overview](/creative-dubbing). ## Step 1: Upload Your Source File ![Dubbing landing screen. Header reads Dubbing, with a green pill showing remaining free time (e.g. 54min 44sec left), a Feedback button, and a black plus New dub button. Below, a GET STARTED label leads into the headline Dub any video into 12 Indian languages, with the subtitle Upload a video, pick target languages, and keep your speaker's voice. Below that, four gradient category cards, each with an icon, a title, three bullet points, and its own call-to-action button: Dub educational content (lotus icon) with button Dub a lecture; Dub drama and fiction (globe icon) with button Dub a scene; Dub spiritual content (shield icon) with button Dub a discourse; Dub Reels and Shorts (play icon) with button Dub a reel.](https://files.buildwithfern.com/https://sarvam-api-docs.docs.buildwithfern.com/c47b0501485a5cfb8fdd4fff92087ca9e0945640149f7c1d46523f9e581927a0/sarvam-creative/assets/dubbing-home.png) Click **+ New dub** in the top-right corner, or click one of the category card buttons on the landing page (**Dub a lecture**, **Dub a scene**, **Dub a discourse**, **Dub a reel**) to open the "Create a dub" modal. !\[Create a dub modal, Step 1 of 2, titled Add your video, shown over a blurred background list of past dub projects. A bordered dropzone reads Drag and Drop or click to upload, with the caption Video (MP4, MOV) or Audio (MP3, WAV) and an Upload button on the right. Below the dropzone, a text link reads or record a video. The modal footer has Cancel and Next buttons.]\(../../assets/Dub part 1.png) * The dropzone accepts **video (MP4, MOV) or audio (MP3, WAV)** - or click **or record a video** to capture footage directly instead of uploading a file. Upload a video or audio file, or attach an accessible social URL. * Uploads are capped at **2 GB per file**. * A URL link skips the local download-then-upload round trip for content you've already published (e.g. a YouTube or social link). * The modal displays your uploaded file's name, size, and duration once attached (e.g. "165.2 MB ยท 5:16") before you move to the next step. ## Step 2: Add Dubbing Details ![Create a dub modal, Step 2 of 2, titled Add dubbing details, with an attached file Demo Video.mp4 at 132.6 MB and 13:30 duration. An editable Project name text field is pre-filled from the source filename. Below that, a two-column row holds Source language (a dropdown with a colored icon, set to Hindi) and Number of speakers (a dropdown, set to 1 speaker). Below that, Target languages is shown as removable tag chips (e.g. Gujarati, Malayalam, each with an x to remove) with a dropdown to add more. A Voice dropdown is set to Clone speaker voice. A Translation style dropdown is set to Auto. At the bottom, a credit summary reads 1,024 divided by 1,00,090.25 credits, with the note 1 minute of dubbed output equals 80 credits. The modal footer has Back and Create dub buttons.](https://files.buildwithfern.com/https://sarvam-api-docs.docs.buildwithfern.com/58546084035ed99e7529fb352a5774e09527a03863596ca783ee2df40b3882b6/sarvam-creative/assets/dubbing-create-modal.png) The **Project name** field is pre-filled from your source filename - edit it to something you'll recognize later, especially if you're running several dubs at once. Search or scroll the **Source language** dropdown and select the language actually spoken in your file. * Each language shows a colored icon alongside its name, making the list easy to scan visually as well as by search. * This tells the model which phonemes and speech patterns to expect, which affects transcription and speaker-separation accuracy before translation even starts. Choose a count from the **Number of speakers** dropdown (1, 4, 5, 6, 7, 8, and more on scroll). * Round upward for multi-speaker conversations - undercounting is worse than overcounting. * Merging two distinct speakers into one slot blends their voices in the output, which is much harder to fix in the editor than simply merging an unused extra slot. Add as many languages as you need to the **Target languages** field. Each one appears as a removable tag (with an x), and the dropdown stays open to add more. * Real-world usage skews heavily toward Hindi and Telugu, with the full set covering most major Indian languages plus English. * Adding multiple targets in one pass produces several localized versions from a single upload - no need to re-process the source per language. Choose how the dubbed voice should be generated from the **Voice** dropdown: * **Clone speaker voice** - zero-shot vocal trait tracking. Use this when audience recognition of the original speaker matters (a host, a founder, a recurring instructor). This is the default. * **Use Sarvam voices** - native artist personas. Faster to review since the persona is already familiar and consistent across projects. Choose a style from the dropdown, or leave it on **Auto**: * **Auto** - automatically picks the best style for the content. Default. * **Formal** - polished, professional language for official content. * **Urban colloquial** - modern, trend-aware localization with urban phrasing and idioms. * **Standard colloquial** - everyday spoken language that feels natural without being overly trendy. * **Traditional colloquial** - conventional spoken language that preserves local linguistic and cultural nuance. * Style changes register and word choice, not just vocabulary - a serious lecture translated in `Urban colloquial` style will read as too casual, even if every fact is correct. Click **Create dub** to dispatch the file to the localization pipeline. * If the banner reads "The video is fully free," this dub won't draw against your free minutes or credits. * Setup fields lock once submitted - double-check source language and speaker count first, since fixing them afterward means starting a new dub rather than editing this one. ## Track Progress ![Processing video dialog showing a 50 percent circular progress indicator, a linear progress bar, and a Status History timeline listing pipeline stages: Translating (Running, started 23 seconds ago), Transcribing (Done, with start and end times and duration), and Processing video (Done, with start and end times and duration). A Go to Projects button sits at the bottom.](https://files.buildwithfern.com/https://sarvam-api-docs.docs.buildwithfern.com/c2fa5f1c8360d262c10bcd3c7e96db96275174deaa23ae7ea3b646d34c558819/sarvam-creative/assets/dubbing-processing.png) After you click **Create dub**, a processing dialog opens automatically so you always know what's happening next - you're never left staring at a blank screen wondering if anything happened. * The **Status History** timeline shows each pipeline stage in order (processing video, transcribing, translating, and so on) as it runs, with a `Running` or `Done` tag and how long each stage took. * You don't have to wait on this screen. Click **Go to Projects** to navigate away - the dub keeps processing in the background, and the project will show as "Review Ready" once it's done. Once your dub reaches "Review Ready" status, head to [Editing a Dub](/creative-dubbing-edit) to refine it.