Sarvam AI

AI dubbing forrecorded webinars

Dub recorded webinars, panels and Q&A sessions into Indian languages. Separate speakers and review terminology 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 recorded webinars translates full sessions, panels and Q&A into Indian languages, with every speaker kept distinct, as an alternative to subtitle-only webinar translation.

  • Expert webinars

    One or two speakers presenting to an audience. Full sessions, including Q&A, are dubbed with every speaker kept distinct.

  • Panel discussions

    A moderator with several panellists.

  • Q&A sessions

    Audience questions answered live, then recorded.

  • Product launch sessions

    Recorded announcements and demos.

See the complete dubbing workflow

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

What matters when
dubbing webinars

A recorded webinar is an hour of panellists, slides and audience questions. Its value is in the detail, so the dub has to keep every speaker clear and every term exact.

Separate panellists and questioners

Set the speaker count to cover the moderator, panel and audience. Each voice is separated and cloned, so the Q&A still reads as a conversation.

Review terminology

Domain terms can come back translated too literally. Fix them in their timestamped block and regenerate only those lines.

Handle long recordings

Upload the full session. Through the API, the Business plan accepts recordings up to four hours, so a webinar does not need to be split.

Review every line before export

Keep every speaker clear and every term exact across a full session.

Multi-speaker separation

Separate moderator, panellists and audience questions.

Line-level editing

Correct domain terms and product names in each block.

Original speaker voice

Keep each panellist's own voice in every language.

Regenerate individual blocks

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

Translation register

Formal suits expert panels; Auto suits community sessions.

Subtitles

Request an SRT per language for on-demand replays.

Audio mix

Even out room sound under the dubbed voices.

Dubbing API

Dub each recording as soon as your webinar platform exports it.

How dubbing works

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

GST filing webinar · Q&A Step 1 of 4 · Upload

Drop a video or audio file

MP4, MOV, MP3 or WAV

gst-webinar-qna.mp40%

165.2 MB · 5:16

Source language
English
Number of speakers
4
Voice
Clone speaker voice
Translation style
Auto
Target languages
HindiMarathiGujarati
  1. 41:10 · Moderator

    We have time for one more question.

    हमारे पास एक और सवाल का समय है।

  2. 41:14 · Attendee

    Does the new rule apply to quarterly filers?

    क्या नया नियम तिमाही रिटर्न भरने वालों पर भी लागू है?

  3. 41:19 · Speaker Regenerate

    Yes, from the October return onwards.

    हाँ, अक्टूबर के रिटर्न से।

  • Hindi MP4WAVSRT
  • Marathi MP4WAVSRT
  • Gujarati MP4WAVSRT

Dub webinars 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 every recording as your webinar platform exports it. Each job returns replays and SRT captions in 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("gst-webinar-qna.mp4")

job = client.dubbing.create(
    source_language_code="en-IN",
    target_language_codes=["hi-IN", "mr-IN", "gu-IN"],
    export_options=["video", "audio", "srt"],
    voice_cloning=True,
    num_speakers=4,
    job_name="gst-webinar-qna",
)
client.dubbing.upload(job.data.upload_url, media)
client.dubbing.start(job_id=job.data.job_id)

Security and privacy

Source files and voice data are encrypted in transit. Sarvam does not use uploaded content to train its models. Sarvam maintains ISO 27001:2022 certification and a SOC 2 Type II report.

Content controls
Private
Source files
Encrypted in transit
Voice data
Encrypted in transit
Model training
Not used

Frequently asked questions

Can panels and Q&A sessions 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.

Can terminology be reviewed before export?

Yes. Every translated line is editable before export. Correct a name, product term or phrase in its timestamped block, then regenerate only that block.

How long can a recorded webinar 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 the replay?

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.

Is uploaded content used for model training?

No. Source files and voice data are encrypted in transit, and Sarvam does not use uploaded content to train its models.

Dub other kinds of content

Try AI dubbing Dub your last webinar and publish the replay in Hindi, Marathi or Gujarati.

Upload video