Sarvam AI

AI dubbing forgaming

Dub recorded character dialogue and cutscenes into Indian languages while keeping speakers distinct. Review and edit dialogue before export.
Indian languages
12
Every speaker's voice
Cloned
Starting price
₹40/min

CH 02

HINDI DUB

Use the remote to change the dub. Each channel is the same stand-up set.

What you can dub

AI dubbing for gaming translates recorded character dialogue and cutscenes into Indian languages, keeping each character in a distinct cloned voice and delivering isolated audio for your build.

  • Cutscenes

    Scripted scenes with several characters and a fixed timing. Each character gets a distinct cloned voice, and you can export isolated audio for your build.

  • Character dialogue

    Recorded lines for heroes, companions and villains.

  • Trailers and launch videos

    Marketing cuts for each regional launch.

  • Tutorial voiceovers

    Narrated onboarding that teaches players the controls.

See the complete dubbing workflow

Follow one video through upload, dubbing, transcript review, line edits and export.

What matters when
dubbing games

Players spend hours with a cast. If two characters start to sound alike or a battle cry loses its edge, the world stops feeling built for them.

Keep every character distinct

Set the speaker count for each cutscene. Sarvam separates the voices before translating and clones each one, so the cast stays recognisable in Hindi or Telugu.

Keep expressive dialogue

Voice cloning carries each actor's vocal traits into the dubbed line, and the translation is fitted to the original timing so a shout still lands on its beat.

Deliver audio your engine can use

Through the API, request the dubbed audio as an isolated WAV track per language and bring it into your localisation workflow.

Review every line before export

Keep the cast recognisable and ship clean audio into your build.

Multi-speaker separation

Separate every character in a scene before translation.

Original speaker voice

Clone each actor's voice, or cast a Sarvam voice for new characters.

Line-level editing

Fix lore names, spells and places in their timestamped block.

Regenerate individual blocks

Re-voice one line after a writing change.

Translation register

Use Urban colloquial for banter or Formal for royal and ceremonial characters.

Audio mix

Balance dialogue against score and effects in cutscenes.

Lip sync

Dubbed dialogue is aligned with on-screen character movement in recorded cutscenes.

Dubbing API

Return isolated WAV dialogue per language into your localisation pipeline.

How dubbing works

Every dub goes through the same four steps in the Sarvam workspace.

Chapter 4 · Cutscene 2 Step 1 of 4 · Upload

Drop a video or audio file

MP4, MOV, MP3 or WAV

ch4-cutscene-2.mp40%

165.2 MB · 5:16

Source language
English
Number of speakers
3
Voice
Clone speaker voice
Translation style
Auto
Target languages
HindiTeluguTamil
  1. 00:31 · Kaira

    The gate won't hold for long.

    ये दरवाज़ा ज़्यादा देर नहीं टिकेगा।

  2. 00:34 · Veer

    Then we don't wait for it to break.

    तो हम इसके टूटने का इंतज़ार नहीं करेंगे।

  3. 00:37 · Kaira Regenerate

    Get the crew. We move at dawn.

    सबको इकट्ठा करो। हम सुबह निकलेंगे।

  • Hindi MP4WAVSRT
  • Telugu MP4WAVSRT
  • Tamil MP4WAVSRT

Dub games into a specific
language

हिन्दीHindi · hi-IN
தமிழ்Tamil · ta-IN
తెలుగుTelugu · te-IN
বাংলাBengali · bn-IN
मराठीMarathi · mr-IN
ગુજરાતીGujarati · gu-IN
ಕನ್ನಡKannada · kn-IN
മലയാളംMalayalam · ml-IN
ਪੰਜਾਬੀPunjabi · pa-IN
ଓଡ଼ିଆOdia · or-IN

Build dubbing into
your workflow

Feed recorded dialogue straight into your localisation workflow. Each job returns isolated WAV audio and SRT for every language you list.

  • 12 Indian languages from one upload
  • Dubbed video, isolated audio and SRT subtitles for every language
  • Every speaker keeps their own cloned voice
Read dubbing API docs Get your API key
Python
import os
from pathlib import Path
from sarvamai import SarvamAI

client = SarvamAI(
    api_subscription_key=os.environ["SARVAM_API_KEY"]
)
media = Path("ch4-cutscene-2.mp4")

job = client.dubbing.create(
    source_language_code="en-IN",
    target_language_codes=["hi-IN", "te-IN", "ta-IN"],
    export_options=["video", "audio", "srt"],
    voice_cloning=True,
    num_speakers=3,
    job_name="ch4-cutscene-2",
)
client.dubbing.upload(job.data.upload_url, media)
client.dubbing.start(job_id=job.data.job_id)

Frequently asked questions

Can Sarvam separate several characters in one scene?

Yes. Set the number of speakers when you create the dub, and Sarvam separates each voice before translating. Round up if you are unsure, because two speakers merged into one slot blend together in the output. Setup fields lock once the dub is created.

Can character dialogue retain the original speaker's voice?

Yes. Clone speaker voice is the default setting. It tracks each original speaker's vocal traits and carries them into every target language. You can choose a Sarvam voice instead.

Can individual dialogue lines be edited?

Yes. Each translated line sits in a timestamped block. Edit the text, regenerate that block's audio and compare it with the original before you export. The rest of the dub stays as it was.

Can dubbed audio be exported separately from video?

Yes. Through the dubbing API, add audio to export_options and each target language returns the dubbed track as a WAV file, with or without the video.

Can the Dubbing API be used inside a localisation workflow?

Yes. Create a dubbing job per file with the dubbing API, list the target languages and export formats, then poll the job and download each export. One job covers every language you list.

Dub other kinds of content

Try AI dubbing Dub one cutscene and hear your cast in Hindi, Telugu or Tamil before you commit a chapter.

Upload video