YouTube API: Get video transcript
Returns the spoken captions and timed segments of a YouTube video, given a video link or a title (top search match). Only captions the video has are returned.
Unofficial. Not affiliated with or endorsed by YouTube.
Inputs
Values from the run on Oct 27, 2026, shown under Output.
- Video, required
video A YouTube video link or its title, for example https://www.youtube.com/watch?v=Ks-_Mh1QhMc.
https://www.youtube.com/watch?v=Ks-_Mh1QhMc
- Language optional
language Caption language name or code, for example Spanish or es; defaults to the original caption language.
Default
.
Input as JSON
{ "video": "https://www.youtube.com/watch?v=Ks-_Mh1QhMc" , "language": ""}Output
{ "segments": [ { "text": "Translator: Joseph Geni Reviewer: Morton Bast", "start_time": "0:00", "start_seconds": 0, "duration_seconds": 7 }, { "text": "So I want to start by offering you a free no-tech life hack,", "start_time": "0:15", "start_seconds": 15.967, "duration_seconds": 5.398 }, { "text": "and all it requires of you is this:", "start_time": "0:21", "start_seconds": 21.389, "duration_seconds": 2.597 } ], "transcript": "Translator: Joseph Geni Reviewer: Morton Bast\nSo I want to start by offering you a free no-tech life hack,\nand all it requires of you is this:\nthat you change your posture for two minutes.\nBut before I give it away, I want to ask you to right now\ndo a little audit of your body and what you're doing …", "video_link": "https://www.youtube.com/watch?v=Ks-_Mh1QhMc" , "video_title": "Your Body Language May Shape Who You Are | Amy Cuddy | TED", "auto_generated": false, "caption_language": "English", "available_language_codes": [ "sq", "ar", "hy" ]}Code
curl https://api.fous.com/v1/runs \ -H "Authorization: Bearer $FOUS_API_KEY" \ -H "Content-Type: application/json" \ -d '{"method":"youtube.com/get_video_transcript","input":{"video":"https://www.youtube.com/watch?v=Ks-_Mh1QhMc","language":""}}' # Save as fous.py, then run: python3 fous.pyimport json, os, timefrom urllib.error import HTTPErrorfrom urllib.request import Request, urlopenAPI = "https://api.fous.com/v1/runs" KEY = os.environ["FOUS_API_KEY"]HEADERS = { "Authorization": f"Bearer {KEY}", "Content-Type": "application/json" ,}def call(url, body=None): data = json.dumps(body).encode() if body else None request = Request(url, data, HEADERS) try: with urlopen(request, timeout=120) as r: return r.status, json.load(r) except HTTPError as error: message = json.load(error)["error"]["message"] raise RuntimeError(message) from errorstatus, run = call(API, { "method": "youtube.com/get_video_transcript" , "input": { "video": "https://www.youtube.com/watch?v=Ks-_Mh1QhMc" , "language": "" }})# 202: still going after 30 s. Ask again until it ends.while status == 202: time.sleep(2) status, run = call(f"{API}/{run['id']}")print(json.dumps(run["data"], indent=2))// Save as fous.mjs, then run: node fous.mjsconst api = "https://api.fous.com/v1/runs" ;const headers = { Authorization: `Bearer ${process.env.FOUS_API_KEY}`, "Content-Type": "application/json" ,};let response = await fetch(api, { method: "POST", headers, body: JSON.stringify({ "method": "youtube.com/get_video_transcript" , "input": { "video": "https://www.youtube.com/watch?v=Ks-_Mh1QhMc" , "language": "" } }), signal: AbortSignal.timeout(120_000),});let run = await response.json();// 202: still going after 30 s. Ask again until it ends.while (response.status === 202) { await new Promise((done) => setTimeout(done, 2_000)); response = await fetch(`${api}/${run.id}`, { headers }); run = await response.json();}if (!response.ok) throw new Error(run.error.message);console.log(run.data);# Connect your agent to Fous once, over MCP (Streamable HTTP):# https://api.fous.com/mcp# Set FOUS_API_KEY first: create a key at https://app.fous.com/keys.# Claude Codeclaude mcp add \ --scope user \ --transport http fous https://api.fous.com/mcp \ --header "Authorization: Bearer ${FOUS_API_KEY:?Set FOUS_API_KEY to your Fous API key}"# Codexcodex mcp add fous \ --url https://api.fous.com/mcp \ --bearer-token-env-var FOUS_API_KEY# Cursor, VS Code, Windsurf, Cline and morenpx -y add-mcp https://api.fous.com/mcp -g -n fous \ --header "Authorization: Bearer ${FOUS_API_KEY:?Set FOUS_API_KEY to your Fous API key}"# Then ask your agent:# "Use Fous to run youtube.com/get_video_transcript# with {"video":"https://www.youtube.com/watch?v=Ks-_Mh1QhMc","language":""}"Over HTTP, the answer’s data holds the output. A run still going after 30 seconds answers 202 with its id: ask GET /v1/runs/{id} until it ends.
Schema
Input schema
{ "type": "object", "required": [ "video" ], "properties": { "video": { "type": "string", "description": "A YouTube video link or its title, for example https://www.youtube.com/watch?v=Ks-_Mh1QhMc." }, "language": { "type": "string", "default": "", "description": "Caption language name or code, for example Spanish or es; defaults to the original caption language." } }}Output schema
{ "type": "object", "required": [ "video_title", "video_link", "caption_language", "auto_generated", "transcript", "segments", "available_language_codes" ], "properties": { "segments": { "type": "array", "items": { "type": "object", "required": [ "start_time", "text", "start_seconds", "duration_seconds" ], "properties": { "text": { "type": "string" }, "start_time": { "type": "string" }, "start_seconds": { "type": "number", "x-fous-developer": true }, "duration_seconds": { "type": "number", "x-fous-developer": true } }, "additionalProperties": false } }, "transcript": { "type": "string" }, "video_link": { "type": "string" }, "video_title": { "type": "string" }, "auto_generated": { "type": "boolean" }, "caption_language": { "type": "string" }, "available_language_codes": { "type": "array", "items": { "type": "string" }, "x-fous-developer": true } }, "additionalProperties": false}- Price
- 1 credit per completed run (1¢ with pay as you go); failed runs are free.
- Method
youtube.com/get_video_transcript- Returns
- video title, link, caption language, auto-generated flag, transcript text, timed segments, available caption languages
Use it from your agent
Give your agent this line. It reads SKILL.md, gets a Fous API key and connects the Fous MCP server. Its run then takes the method youtube.com/get_video_transcript with the inputs above.
Ask your agent
- Get me the full transcript of https://www.youtube.com/watch?v=dQw4w9WgXcQ with timestamps
- What does the speaker actually say in Simon Sinek's 'Start With Why' TED talk? I need the text of the captions.
- Pull the Spanish captions for https://youtu.be/8jPQjjsBbIc so I can study the vocabulary
- I need the YouTube captions for 'How to Make Sourdough Bread Joshua Weissman' in plain text, and tell me if they're auto-generated
- Which caption languages are available for this YouTube video, and can you give me the Japanese ones: https://www.youtube.com/watch?v=aircAruvnKk
See more
All YouTube methodsGets public details and statistics for one YouTube video by link, ID or title. A title selects the top search match.
youtube.com/get_videoGets public top-level comments on a YouTube video, found by link, video ID or title. Reply text is not included.
youtube.com/get_video_commentsGets a public YouTube channel's profile, links and statistics from its name, @handle or link. Subscriber totals may be rounded as YouTube displays them.
youtube.com/get_channelLists a YouTube channel's public videos, Shorts, or live uploads, newest first or most popular first, along with channel details. Counts and dates taken from displayed text may be approximate.
youtube.com/list_channel_videosLists the latest weekly YouTube Music Top Songs chart for a country or globally, with ranks, weekly views and video links.
youtube.com/list_top_songsFinds a company's verified YouTube channel by name and returns its name, link, subscriber count, description, country and official website when identifiable.
youtube.com/find_company_channelTranslates up to 5,000 characters on Google Translate, with the detected source language, Latin-letter pronunciation when shown, and dictionary alternatives for words or short phrases.
translate.google.com/translate_textGets a public Vimeo video's title, creator, play, like and comment counts, length, upload date, description, tags, thumbnail and link from its video link.
vimeo.com/get_video