Sarvam AI

AI dubbing fornews videos

Dub recorded bulletins and interviews into Indian languages. Review names, places and spoken text 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 news videos translates recorded bulletins, packages and interviews into Indian languages, with every name and place open to review before a segment is published.

  • Recorded bulletins

    Anchor-led segments for each language channel. Names and places stay open to review in every translated line before a segment is published.

  • Field packages

    Reporter pieces with ambient sound and local voices.

  • Interviews

    One-on-one and panel conversations with several speakers.

  • Explainers and features

    Longer stories that stay relevant after the news cycle.

See the complete dubbing workflow

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

What matters when
dubbing news videos

News is judged on accuracy. A misspoken name or place is a correction the next day, and a newsroom has to publish before the story moves on.

Get names and places right

Proper nouns are editable in every translated block. Check each official, town and organisation before export, and regenerate only the lines you fix.

Keep anchors, reporters and guests distinct

Set the speaker count for a bulletin or panel. Each voice is separated and cloned, so the audience always knows who is speaking.

Publish while the story is current

Add every target language to one dub. Each edition comes from the same upload, so the Hindi and Tamil versions are ready together.

Review every line before export

Keep names exact and speakers clear across every language edition.

Line-level editing

Check officials, places and organisations in each timestamped block.

Multi-speaker separation

Separate anchor, reporters and interviewees before translation.

Original speaker voice

Keep the anchor's own voice across your language channels.

Regenerate individual blocks

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

Translation register

Use Formal for bulletins and Auto for field interviews.

Subtitles

Request an SRT per language for web and social players.

Audio mix

Keep ambient field sound under the dubbed voice.

Dubbing API

Send recorded segments from your newsroom system as they are filed.

How dubbing works

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

Evening bulletin · Segment 2 Step 1 of 4 · Upload

Drop a video or audio file

MP4, MOV, MP3 or WAV

bulletin-seg-2.mp40%

165.2 MB · 5:16

Source language
English
Number of speakers
3
Voice
Clone speaker voice
Translation style
Auto
Target languages
HindiTamilMalayalamBengali
  1. 01:05 · Anchor

    Heavy rain has closed schools across Kerala.

    भारी बारिश के कारण पूरे केरल में स्कूल बंद हैं।

  2. 01:09 · Reporter

    Reporting from Kozhikode.

    हम कोझिकोड से रिपोर्ट कर रहे हैं।

  3. 01:12 · Reporter Regenerate

    Minister Suresh Nair visited the relief camp.

    मंत्री सुरेश नायर ने राहत शिविर का दौरा किया।

  • Hindi MP4WAVSRT
  • Tamil MP4WAVSRT
  • Malayalam MP4WAVSRT
  • Bengali MP4WAVSRT

Dub news videos 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 segments as your newsroom files them. Each job returns every language edition with SRT subtitles for web and social players.

  • 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("bulletin-seg-2.mp4")

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

Frequently asked questions

Can names and place names be corrected 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.

Can interviews with multiple 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 intended for recorded or live news?

The dubbing workspace and API work on recorded video and audio files. Upload a bulletin, package or interview once it is recorded, review it and export each language edition.

Can subtitle files be exported?

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.

What video and audio formats are supported?

The workspace accepts MP4 and MOV video, or MP3 and WAV audio, up to 2 GB per file. The dubbing API also accepts MKV, WebM, AVI, FLV, WMV and M4A.

Dub other kinds of content

Try AI dubbing Dub one recorded segment and check every name in Hindi, Tamil or Malayalam before it airs.

Upload video