A data newsletter item turned into a Hindi podcast

An Our World in Data post on oil production became a two-host podcast in Hindi. Hear it, copy the exact request, and see its cost and what our check found.

How this was made. Audio and video overviews, slide decks, infographics and quizzes are made with Google's Gemini Notebook (formerly NotebookLM), on accounts that AutoContent operates. AutoContent has no agreement with Google. Google can limit or stop this access at any time.

The podcast (Hindi)

Our World in Data: The United States is the world's largest oil producer

PodcastHindi5 min 52 s

0:005:52

Transcript excerpt

Speech-to-text of the output, not edited and without speaker labels. It is part of the sample output.

सबसे बड़ा प्रडूसर? जी हाँ आकडों के मुताबिक, यूएस ने करीब 9 साल पहले ही साउदी अरेबिया को उत्पादन में पीछे छोड़ दिया था और आज ये तेल उत्पादन अपने सबसे उचे स्थर पर है, मतलब एकदम आल टाइम हाई पर रुकिये, नौ साल पहले? अगर UF soil production में इतना आगे निकल गया था तो इस पर इतनी बड़ी चर्चा क्यों नहीं हुई? क्योंकि लोग अभी भी पुराने mindset में अटके हुए है वही ना, क्योंकि मुझे अच्छे से याद है 1990s और 2000s के शुरुवाती दौर में तो US बहर से तेल मंगमाने के लिए जाना जाता था

AI-generated with AutoContent APIDownload MP3Full transcript (TXT)
Length
5 min 52 s
Credits used
10 credits
Cost on the Starter plan
€0.29
Generation time
5 min 20 s
Format
Podcast
Job
Newsletters
Language
Hindi
Generated on
2026-11-02
Make this with the API

This output used 10 credits, which is €0.29 on the Starter plan (€29 per month for 1,000 credits). Failed generations use none. Generation time runs from the request to the finished file; it depends on the sources, the options and the queue.

What came out, and what we would change

We sent one Our World in Data post and asked for the Hindi audio edition of a newsletter item: the key number, how it changed, and one sentence of context, with duration short. The result is a two-host episode of 5 min 52 s in Hindi, with terms such as shale, fracking and OPEC kept in English.

The facts from the post are right: the United States has been the largest oil producer for nine years, since it passed Saudi Arabia; its production fell in the 1990s and early 2000s, rose sharply after 2010, and is at an all-time high; and the data comes from the Energy Institute's Statistical Review of World Energy.

It gives far more than one sentence of context. The hosts explain shale oil, horizontal drilling and hydraulic fracturing, say that the United States went from the largest oil importer to the largest producer, and discuss OPEC's lost pricing power. None of this is in the post, so treat it as the hosts' own background. They also stretch the decline to the end of the 2000s; the post says the 1990s and early 2000s.

The episode took 5 min 20 s to generate and used 10 credits. To keep an edition short and close to the source, say so in the text, for example "only the facts in the post".

The exact request

The body that was sent to POST /content/Create, unchanged, and the same request as curl.

request.json
{
  "resources": [
    {
      "type": "website",
      "content": "https://ourworldindata.org/data-insights/the-united-states-is-the-worlds-largest-oil-producer"
    }
  ],
  "outputType": "audio",
  "duration": "short",
  "text": "The Hindi audio edition of a data newsletter item: the key number, how it changed, and one sentence of context. Do not name the writer.",
  "language": "हिन्दी"
}
curl
curl -X POST "https://api.autocontentapi.com/content/Create" \
  -H "Authorization: Bearer $AUTOCONTENT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"resources":[{"type":"website","content":"https://ourworldindata.org/data-insights/the-united-states-is-the-worlds-largest-oil-producer"}],"outputType":"audio","duration":"short","text":"The Hindi audio edition of a data newsletter item: the key number, how it changed, and one sentence of context. Do not name the writer.","language":"हिन्दी"}'
# then poll until "status" is 100:
curl -H "Authorization: Bearer $AUTOCONTENT_API_KEY" "https://api.autocontentapi.com/content/Status/<request_id>"

How we checked it

Transcript
We transcribed the output with Whisper large-v3-turbo and compared the transcript with the source.
Language
Detected hi, requested hi.
Loudness
-17.8 LUFS integrated, true peak -2.5 dBTP.
Notes
The post's facts are right; the fracking story, the importer point and the OPEC discussion are additions.
Checked on
2026-11-02. Failed generations are run again and never published.