Get YouTube Transcript - DumplingAI Docs

Get YouTube transcript

curl --request POST \
  --url https://app.dumplingai.com/api/v1/get-youtube-transcript \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "videoUrl": "<string>",
  "preferredLanguage": "<string>",
  "includeTimestamps": true,
  "timestampsToCombine": 2
}
'

{
  "language": "<string>",
  "transcript": "<string>"
}

POST

api

get-youtube-transcript

Get YouTube transcript

curl --request POST \
  --url https://app.dumplingai.com/api/v1/get-youtube-transcript \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "videoUrl": "<string>",
  "preferredLanguage": "<string>",
  "includeTimestamps": true,
  "timestampsToCombine": 2
}
'

{
  "language": "<string>",
  "transcript": "<string>"
}

Description

This endpoint extracts the transcript from a specified YouTube video URL, formats the transcript, and optionally includes timestamps.

Endpoint

POST https://app.dumplingai.com/api/v1/get-youtube-transcript

Headers

Content-Type: application/json
Authorization: Bearer <API_KEY> (required)

Request Body

{
  "videoUrl": "string", // Required. The URL of the YouTube video.
  "includeTimestamps": "boolean", // Optional. Whether to include timestamps in the transcript. Default: true.
  "timestampsToCombine": "number", // Optional. The number of timestamps to combine in the transcript. Default: 5.
  "preferredLanguage": "string" // Optional. Preferred language for the transcript.
}

Accepted Values for `preferredLanguage`

The preferredLanguage parameter accepts the following language codes:

Language Code	Language
af	Afrikaans
ak	Akan
sq	Albanian
am	Amharic
ar	Arabic
hy	Armenian
as	Assamese
ay	Aymara
az	Azerbaijani
bn	Bangla
eu	Basque
be	Belarusian
bho	Bhojpuri
bs	Bosnian
bg	Bulgarian
my	Burmese
ca	Catalan
ceb	Cebuano
zh	Chinese
zh-HK	Chinese (Hong Kong)
zh-CN	Chinese (China)
zh-SG	Chinese (Singapore)
zh-TW	Chinese (Taiwan)
zh-Hans	Chinese (Simplified)
zh-Hant	Chinese (Traditional)
hak-TW	Hakka Chinese (Taiwan)
nan-TW	Min Nan Chinese (Taiwan)
co	Corsican
hr	Croatian
cs	Czech
da	Danish
dv	Divehi
nl	Dutch
en	English
en-US	English (United States)
eo	Esperanto
et	Estonian
ee	Ewe
fil	Filipino
fi	Finnish
fr	French
gl	Galician
lg	Ganda
ka	Georgian
de	German
el	Greek
gn	Guarani
gu	Gujarati
ht	Haitian Creole
ha	Hausa
haw	Hawaiian
iw	Hebrew
hi	Hindi
hmn	Hmong
hu	Hungarian
is	Icelandic
ig	Igbo
id	Indonesian
ga	Irish
it	Italian
ja	Japanese
jv	Javanese
kn	Kannada
kk	Kazakh
km	Khmer
rw	Kinyarwanda
ko	Korean
kri	Krio
ku	Kurdish
ky	Kyrgyz
lo	Lao
la	Latin
lv	Latvian
ln	Lingala
lt	Lithuanian
lb	Luxembourgish
mk	Macedonian
mg	Malagasy
ms	Malay
ml	Malayalam
mt	Maltese
mi	Māori
mr	Marathi
mn	Mongolian
ne	Nepali
nso	Northern Sotho
no	Norwegian
ny	Nyanja
or	Odia
om	Oromo
ps	Pashto
fa	Persian
pl	Polish
pt	Portuguese
pa	Punjabi
qu	Quechua
ro	Romanian
ru	Russian
sm	Samoan
sa	Sanskrit
gd	Scottish Gaelic
sr	Serbian
sn	Shona
sd	Sindhi
si	Sinhala
sk	Slovak
sl	Slovenian
so	Somali
st	Southern Sotho
es	Spanish
su	Sundanese
sw	Swahili
sv	Swedish
tg	Tajik
ta	Tamil
tt	Tatar
te	Telugu
th	Thai
ti	Tigrinya
ts	Tsonga
tr	Turkish
tk	Turkmen
uk	Ukrainian
ur	Urdu
ug	Uyghur
uz	Uzbek
vi	Vietnamese
cy	Welsh
fy	Western Frisian
xh	Xhosa
yi	Yiddish
yo	Yoruba
zu	Zulu

Responses

Success (200)

Returns the transcript of the specified YouTube video and the language that was actually returned.

{
  "transcript": "string",
  "language": "string"
}

Content-Type: application/json
X-RateLimit-Limit: The rate limit for the user.
X-RateLimit-Remaining: The remaining number of requests for the user.

Bad Request (400)

Returned if the request is invalid or missing required parameters.

{
  "error": "Error message describing the issue"
}

Not Found (404)

Returned if no subtitles are found for the video.

{
  "error": "No subtitles found for the video: <videoID>"
}

Internal Server Error (500)

Returned if there’s an error during the transcript extraction process.

{
  "error": "Error message describing the issue"
}

Example Request

curl -X POST https://app.dumplingai.com/api/v1/get-youtube-transcript \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
  "videoUrl": "https://www.youtube.com/watch?v=example",
  "includeTimestamps": true,
  "timestampsToCombine": 5,
  "preferredLanguage": "en"
}'

Example Response

{
  "transcript": "00:00 - Welcome to this video.\n00:05 - Today we'll be discussing...",
  "language": "en"
}

Notes

The videoUrl parameter must be a valid YouTube video URL.
If includeTimestamps is set to false, the transcript will not include timestamp information.
The timestampsToCombine parameter determines how many individual transcript segments are combined into a single line with a timestamp.
The preferredLanguage parameter allows you to request a specific transcript language.
If the requested preferredLanguage is not available but the video has captions in another language, the endpoint will automatically fall back to the first available transcript instead of failing.
The language field in the response always reflects the transcript language that was actually returned, which may differ from preferredLanguage.
This endpoint uses 20 credits per request.
The transcript extraction attempts to retrieve the captions of a YouTube video. Some videos have captions disabled, this action will fail on these videos.

Rate Limiting

Rate limit headers (X-RateLimit-Limit and X-RateLimit-Remaining) are included in the response to indicate the user’s current rate limit status.

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

videoUrl

string<uri>

required

Full YouTube video URL.

preferredLanguage

string

Preferred transcript language code. If unavailable, DumplingAI falls back to the first available transcript language for the video.

includeTimestamps

boolean

Include timestamps in the transcript output.

timestampsToCombine

integer

Number of consecutive transcript segments to merge.

Required range: x >= 1

requestSource

enum<string>

Optional identifier describing where the API request originated.

Available options:

API,

WEB,

MAKE_DOT_COM,

ZAPIER,

N8N,

PLAYGROUND,

DEFAULT_AUTOMATION,

AGENT_PREVIEW,

AGENT_LIVE,

AUTOPILOT,

STUDIO

Response

Transcript retrieved.

language

string

Transcript language returned by the API. This may differ from preferredLanguage when DumplingAI falls back to the first available transcript.

transcript

string

Transcript formatted as newline separated segments.

Credit Costs Get YouTube Video

​Description

​Endpoint

​Headers

​Request Body

​Accepted Values for preferredLanguage

​Responses

​Success (200)

​Bad Request (400)

​Not Found (404)

​Internal Server Error (500)

​Example Request

​Example Response

​Notes

​Rate Limiting

Authorizations

Body

Response

Description

Endpoint

Headers

Request Body

Accepted Values for `preferredLanguage`

Responses

Success (200)

Bad Request (400)

Not Found (404)

Internal Server Error (500)

Example Request

Example Response

Notes

Rate Limiting