Sarvam AI

AI dubbing forevent recordings

Dub recorded keynotes, panels and sessions into Indian languages while keeping speakers distinct.
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 event recordings translates recorded keynotes, panels and sessions into Indian languages after the event, keeping every speaker in their own voice.

  • Keynotes

    Leadership talks recorded on stage. Dub the recording after the event, with the speaker kept in their own voice in every language.

  • Panels

    Moderated discussions with several speakers.

  • Breakout sessions and workshops

    Smaller sessions with hands-on content.

  • Conference highlights

    Edited reels published after the event.

See the complete dubbing workflow

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

What matters when
dubbing event recordings

An event recording has one shot at a second audience. A keynote has to keep its energy, and a panel has to keep its people apart, in every language it is published in.

Keep keynotes in the speaker's voice

Voice cloning carries the speaker's vocal traits into each language, so the Hindi edition of a keynote still sounds like the person on stage.

Keep panels distinct

Set the speaker count for panel sessions. Each voice is separated and cloned before translation, so every panellist stays recognisable.

Handle full-length sessions

Upload complete recordings. Through the API, the Business plan accepts files up to four hours, and one job covers every language you publish in.

Review every line before export

Give every session a second audience in the languages your attendees speak.

Original speaker voice

Keep each keynote speaker's voice across language editions.

Multi-speaker separation

Separate moderators and panellists before translation.

Line-level editing

Correct speaker names, company names and figures.

Regenerate individual blocks

Re-voice a corrected line without re-dubbing the session.

Translation register

Formal for leadership keynotes, Auto for workshops.

Audio mix

Keep applause and hall sound under the dubbed voice.

Subtitles

Request an SRT per language for on-demand pages.

Dubbing API

Dub a whole event programme, one job per session.

How dubbing works

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

Annual summit · Keynote Step 1 of 4 · Upload

Drop a video or audio file

MP4, MOV, MP3 or WAV

summit-keynote.mp40%

165.2 MB · 5:16

Source language
English
Number of speakers
1
Voice
Clone speaker voice
Translation style
Auto
Target languages
HindiTamilTeluguKannada
  1. 06:20 · Keynote

    Five years ago, we had one factory.

    पाँच साल पहले हमारे पास एक ही फ़ैक्ट्री थी।

  2. 06:24 · Keynote

    Today we ship to forty countries.

    आज हम चालीस देशों में सामान भेजते हैं।

  3. 06:28 · Keynote Regenerate

    And we're only getting started.

    और ये तो बस शुरुआत है।

  • Hindi MP4WAVSRT
  • Tamil MP4WAVSRT
  • Telugu MP4WAVSRT
  • Kannada MP4WAVSRT

Dub event recordings 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

Dub an entire programme after the event. Create one job per session and publish every language edition with SRT captions.

  • 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("summit-keynote.mp4")

job = client.dubbing.create(
    source_language_code="en-IN",
    target_language_codes=["hi-IN", "ta-IN", "te-IN", "kn-IN"],
    export_options=["video", "audio", "srt"],
    voice_cloning=True,
    num_speakers=1,
    job_name="summit-keynote",
)
client.dubbing.upload(job.data.upload_url, media)
client.dubbing.start(job_id=job.data.job_id)

Frequently asked questions

Can recorded keynotes keep the 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 panels with several speakers be dubbed?

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.

Is Sarvam Dubbing for live or recorded events?

The dubbing workspace and API work on recorded video and audio files. Upload each session once it is recorded, review it and export every language edition.

How long can a session recording be?

The workspace accepts files up to 2 GB. Through the API, the Starter plan allows 2 GB and one hour per file, Pro allows 3 GB and one hour, and Business allows 4 GB and four hours.

Can I export subtitles for each session?

Yes, through the dubbing API. Add srt to export_options and each target language returns a subtitle file timed to the dub, alongside the video or audio you request.

Dub other kinds of content

Try AI dubbing Dub your keynote recording and publish it in Hindi, Tamil or Telugu.

Upload video