A video's full transcript
social_youtube_subtitles is a $0.20 GET request on the Wuthering AI API. Read the complete timestamped transcript of a YouTube video. It answers complete JSON, and a call that fails is not charged.
Endpoint
GET /v1/social_youtube_subtitles
Price per successful call
$0.20
Failed calls
Not charged
curl 'https://wutheringai.com/v1/social_youtube_subtitles?video_id=…&token=YOUR_TOKEN'
What does social_youtube_subtitles return, and when should you call it?
Return the full transcript of a YouTube video as timestamped segments.
This turns hours of video into text an agent can actually reason over, which is the only practical way to mine conference talks, product demos, and competitor walkthroughs at scale. Costs roughly three times a standard call. Only videos with available captions return text.
Returns: an ordered list of segments, each with text, start_time, end_time, and duration_time in seconds.
These are rolling caption fragments, not sentences: consecutive segments OVERLAP in both time and wording, and any single one is likely to start or end mid-thought. To quote someone accurately, join several segments and de-duplicate the repeated words rather than citing one segment verbatim. A video with no track in the language asked for is refused rather than answered empty, so a refusal usually means the wrong language rather than a video that cannot be read at all.
Use to extract claims, pricing, and objections from video. Don't use to find videos, which is wuthering_social_youtube_search.
What parameters does social_youtube_subtitles take?
social_youtube_subtitles accepts 3 parameters, of which 1 is required. Array values are comma-separated on the query string.
| Parameter | Type | Required | Description |
|---|---|---|---|
| video_id | string | yes | YouTube video id, the part after v= in a watch URL. Not the full URL. |
| location_code | number | no | Numeric location code to scope results to. Defaults to 2840 (United States). Search volume and competition vary sharply by country, so set this when the question is about a specific market.Defaults to 2840 |
| language_code | string | no | Which caption track to READ, for example 'en' or 'de'. Defaults to 'en'. This selects a track rather than translating one: a video captioned only in Korean is refused for 'en' and returns its transcript for 'ko'. Pass the language the video was captioned in, not the language you would prefer to read.Defaults to en |
Reference for social_youtube_subtitles · last updated · published by Wuthering AI