Sarvam AI

AI dubbing fordocumentaries

Dub narration and recorded interviews into Indian languages while retaining each speaker's voice and delivery.
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 documentaries translates narration and recorded interviews into Indian languages, keeping the narrator and every interviewee in their own voice.

  • Feature documentaries

    Long-form films with narration and many interviews. The narrator and every interviewee keep their own voice in each language edition.

  • Documentary series

    Episodic work dubbed episode by episode.

  • Short documentaries

    Brand, NGO and festival shorts.

  • Archival and oral-history footage

    Recorded testimony where the voice matters as much as the words.

See the complete dubbing workflow

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

What matters when
dubbing documentaries

A documentary asks the audience to believe what it hears. The narrator has to stay the narrator, interviewees have to sound like themselves, and every figure has to survive translation.

Separate narrator and interviewees

Set the speaker count to cover the narrator and everyone interviewed. Each voice is separated and cloned, so the film's structure stays audible.

Review names, dates and figures

Every translated line is editable. Check years, numbers and proper nouns against your script before export, and regenerate only the lines you correct.

Hand audio to post-production

Through the API, export an isolated dubbed audio track and SRT for each language, ready for your editor's final mix.

Review every line before export

Keep every voice true to the person and every fact true to the script.

Multi-speaker separation

Separate narrator, interviewees and archival voices.

Original speaker voice

Clone each interviewee's voice so their testimony stays theirs.

Line-level editing

Check dates, figures and names against your script.

Regenerate individual blocks

Re-voice a corrected fact without re-dubbing the act.

Lip sync

Dubbed dialogue is aligned with interviewees' on-screen movements.

Translation register

Formal suits narration; Auto fits conversational interviews.

Audio mix

Keep location sound and score under the dubbed narration.

Subtitles

Request an SRT per language for festival and streaming delivery.

How dubbing works

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

The Last Weavers · Act 2 Step 1 of 4 · Upload

Drop a video or audio file

MP4, MOV, MP3 or WAV

last-weavers-act2.mp40%

165.2 MB · 5:16

Source language
English
Number of speakers
4
Voice
Clone speaker voice
Translation style
Auto
Target languages
HindiBengaliTamil
  1. 18:02 · Narrator

    In 1970, the village had three hundred looms.

    1970 में इस गाँव में तीन सौ करघे थे।

  2. 18:07 · Lakshmi

    My mother taught me before I could read.

    पढ़ना सीखने से पहले ही माँ ने मुझे बुनना सिखा दिया।

  3. 18:12 · Narrator Regenerate

    Today, only eleven remain.

    आज सिर्फ़ ग्यारह करघे बचे हैं।

  • Hindi MP4WAVSRT
  • Bengali MP4WAVSRT
  • Tamil MP4WAVSRT

Dub documentaries 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

Hand your post-production team clean deliverables. Each job returns dubbed video, an isolated WAV audio track and SRT per language.

  • 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("last-weavers-act2.mp4")

job = client.dubbing.create(
    source_language_code="en-IN",
    target_language_codes=["hi-IN", "bn-IN", "ta-IN"],
    export_options=["video", "audio", "srt"],
    voice_cloning=True,
    num_speakers=4,
    job_name="last-weavers-act2",
)
client.dubbing.upload(job.data.upload_url, media)
client.dubbing.start(job_id=job.data.job_id)

Frequently asked questions

Can narration and interviews be dubbed in the same project?

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. Count the narrator as one of the speakers.

Can names and factual wording 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.

Can interviews with several speakers be handled?

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 audio and subtitle files be exported separately?

The workspace exports the reviewed dubbed video. Through the dubbing API, one job can return the dubbed video, an isolated audio track in WAV and an SRT subtitle file for each target language.

Does Sarvam support lip-sync for documentary footage?

Yes. Sarvam aligns translated dialogue with the speaker's on-screen movements. Translations are also fitted to the original timing, so a longer Hindi or Tamil line stays within the speaker's delivery.

Dub other kinds of content

Try AI dubbing Dub one act and check every name and figure in Hindi, Bengali or Tamil.

Upload video