YouTube2Text

GPT: ADX scalping strategy in Python makes 4479% — Transcript

by Algo-trading with Saleh · 3,880 words · 527 segments · language en · Watch on YouTube

Full transcript

  1. 0:00Hey guys, so today I'm going to show you
  2. 0:01a scalping strategy which not only is
  3. 0:04super simple but the result of it is
  4. 0:06probably the best that I have achieved
  5. 0:08yet. First I'm going to show you the
  6. 0:10entry and exit rules of the strategy on
  7. 0:12trading view and then I'm going to use
  8. 0:14GPT to convert those rules into Python
  9. 0:17code so we can run some back test on it.
  10. 0:19So if that all sounds good, let's get
  11. 0:20right into it. First let's talk about
  12. 0:23the entry rules of the strategy. The
  13. 0:25main indicator of this strategy is
  14. 0:27called the directional index. So let's
  15. 0:30add it to our chart. This indicator is
  16. 0:32very simple. We have three lines. The
  17. 0:34red line here is simply the ADX
  18. 0:36indicator which shows us the strength of
  19. 0:39the trend. Because this is a trend
  20. 0:40following strategy. We only want to take
  21. 0:42trades when the volatility is high. And
  22. 0:44that's what the ADX does. So let's add
  23. 0:46the threshold of 50. So we will only
  24. 0:49take trades when this red line here is
  25. 0:51above the threshold. Next, we use this
  26. 0:53blue and the orange line in order to
  27. 0:55determine the direction of the trend. If
  28. 0:57for example in here the blue line is
  29. 0:59above this orange line, we are in an
  30. 1:01uptrend which we can clearly see here.
  31. 1:03And if the orange line crosses the blue
  32. 1:05line, for example in here, we are in a
  33. 1:08clear downtrend. By combining the
  34. 1:10direction of the trend and also the
  35. 1:12strength of it using the ADX, which is
  36. 1:14this red line here, we have a pretty
  37. 1:16good indicator for taking trades when
  38. 1:18the volatility is high. Now, other than
  39. 1:20this indicator, we also use an
  40. 1:22oscillator. Now, you probably already
  41. 1:24know such as the RSI or stocastic, but
  42. 1:27in this strategy, we're going to use
  43. 1:29Williams percentage R. So, let's look it
  44. 1:32up on Trading View. Williams percent
  45. 1:36range.
  46. 1:37It looks like any other oscillator
  47. 1:39except that usually we have the values
  48. 1:42of 20 to 80 for a typical oscalator. But
  49. 1:46for this one, we have minus 80 and minus
  50. 1:5020. And we want to take a long trade,
  51. 1:51for example, in here where the price is
  52. 1:53oversold. And we want to take a short
  53. 1:55trade, for example, in here when the
  54. 1:57price is oversold. And that's it. Those
  55. 1:59are the only two rules that we have for
  56. 2:01this strategy. But now, let's talk about
  57. 2:03the exit rules. Now, for the stop loss,
  58. 2:05I'm going to use a super simple method
  59. 2:07that I actually have never done in my
  60. 2:09previous videos, and that is simply
  61. 2:10using an SMA or moving average. Simple
  62. 2:15but changing the value of it from 9
  63. 2:20into 50.
  64. 2:23So let's hide these two.
  65. 2:26All right. So if we are taking a long
  66. 2:29trade, we want to use this blue line. So
  67. 2:31whenever the price hits this 50 moving
  68. 2:33average, we're saying, hey, the trend is
  69. 2:35over and I don't want to be in this
  70. 2:37trade anymore. And if it's a short
  71. 2:39trade, we again use this moving average.
  72. 2:41And for example in here we would have
  73. 2:43hit our stop loss. As for the take
  74. 2:45profit if it's a short position. So
  75. 2:47let's say this is a short trade that we
  76. 2:48were taking. And let's say we enter the
  77. 2:51trade in here. For the take profit price
  78. 2:53I want it to be the lowest value of the
  79. 2:55price in the last 30 candles. So if you
  80. 2:58do it in here it's going to be at here
  81. 3:01and we would have hit this price at this
  82. 3:03point. Now if it's a long position we
  83. 3:05want to do the opposite. So I want the
  84. 3:07highest value of the price in the last
  85. 3:0930 candles. So for example, if we had
  86. 3:11opened the position in here or in here,
  87. 3:13it doesn't really matter. The highest
  88. 3:15price would have been at this point
  89. 3:17which we would have reached here. Now we
  90. 3:19do have another exit rule of the
  91. 3:21strategy and that is let's say we open a
  92. 3:23long position but for whatever reason
  93. 3:26the direction of the trend has now
  94. 3:28changed. It is now in a downtrend. Then
  95. 3:30we want to close the position. All
  96. 3:32right. Now that we have all the entry
  97. 3:34and exit rules of the strategy, we can
  98. 3:36begin feeding it into our GPT to write
  99. 3:38the Python code for us. So we can run
  100. 3:40some back test on it. Now in case you're
  101. 3:42not familiar with this service which we
  102. 3:44call Jess GPT, it is our own customized
  103. 3:46version of GFT which uses all sorts of
  104. 3:49LL models such as Gemini, deepc cloth or
  105. 3:52whichever edge model really and you can
  106. 3:54get it started with it completely for
  107. 3:56free. But for whatever reason, let's say
  108. 3:58for a privacy concern or let's say you
  109. 4:00don't like the pricing of our website,
  110. 4:02you can watch my previous video which
  111. 4:03I'm going to link somewhere on the
  112. 4:05screen which teaches you how to
  113. 4:06self-hosted yourself. So again, using
  114. 4:08this service is not mandatory, but
  115. 4:10that's what I'm going to use in this
  116. 4:12video. All right. So I simply wrote down
  117. 4:14whatever I just described to you on the
  118. 4:16chart and I'm asking it to write me a
  119. 4:18strategy. And here are the rules. For a
  120. 4:21long position, I want the directional
  121. 4:22indexes plus value, which is this blue
  122. 4:25line here, to be above the minus, which
  123. 4:29is this orange line here. And I also
  124. 4:32want the ADX value to be above 50, which
  125. 4:34again is this red line here. As for the
  126. 4:37stop loss, I want the SMA with a period
  127. 4:39of 50. For the take profit, if it's a
  128. 4:41long position, I want the highest high
  129. 4:43of the last 30 candles. And if it's a
  130. 4:45short position, I want the lowest low of
  131. 4:47the last 30 candles. Also for opted
  132. 4:49position assuming we already have an
  133. 4:51open position close if entry rule is the
  134. 4:54opposite directional now and as for the
  135. 4:56risk management I'm saying risk 3% per
  136. 4:58each trade and use the market order for
  137. 5:01entry and that's all I am feeding this
  138. 5:04LLM. Now, one more thing. I want to
  139. 5:05change the model, but I'm going to have
  140. 5:07to copy this value. Change this into
  141. 5:11cloud set, which is my favorite coding
  142. 5:13model. And paste it again here. And hit
  143. 5:16the enter to get the response.
  144. 5:20And it has started writing it for us.
  145. 5:24This looks really nice.
  146. 5:27Let's wait for it to finish. And boom,
  147. 5:30we're done. Now, usually I change the
  148. 5:31names that these models give to the
  149. 5:33strategy, but I think this one is quite
  150. 5:35nice. So, let's copy it and go to the
  151. 5:37Jess's dashboard and create a new
  152. 5:39strategy and I'm going to paste that
  153. 5:41value here. Next, I'll go to VS Code,
  154. 5:43which is my editor, and I will look it
  155. 5:45up. And then I'm going to go back to
  156. 5:47Jesse GPT, copy this whole thing, go
  157. 5:51back here, and paste it.
  158. 5:53Now, let's go through it, see how it
  159. 5:55looks like. So the definition of ADX
  160. 5:58indicator is perfectly fine. The
  161. 6:00directional index is also fine. The 50
  162. 6:03moving average is great. The highest
  163. 6:06high it is using the max of the last 30
  164. 6:09candles and the index of three. Now
  165. 6:12remember the index of zero is the time
  166. 6:14stamp of the candle. One is the opening
  167. 6:16price. Two is close. The three is the
  168. 6:19high. So this is perfectly right. The
  169. 6:21lowest low is also correct. The inter
  170. 6:23rule for short positions is the DI plus
  171. 6:27must be above the DI minus. The inter
  172. 6:30rule for the long positions is that the
  173. 6:32plus value must be bigger than minus and
  174. 6:35the ADX must be above 50. This is
  175. 6:37correct, but I think it forgot the
  176. 6:39oscalator. Actually guys, I forgot to
  177. 6:41tell the model about the oscalator. So
  178. 6:43let's ask it to add that to the code.
  179. 6:45Please also use an oscalator for the
  180. 6:47entry of the strategy. If the value of
  181. 6:50the Williams percentage R is below minus
  182. 6:5380, we want to look for long positions.
  183. 6:56And if it's above minus20, we want to
  184. 6:58look for short positions. Let's hit
  185. 7:00enter.
  186. 7:05Let's wait for it to finish. All right,
  187. 7:07let's go back here. Copy this value. Go
  188. 7:11back. Paste it here. All right, so let's
  189. 7:13go up. Here's the definition of Williams
  190. 7:16R. And you can see this is correct
  191. 7:18because if I hold the option key I can
  192. 7:21see its definition. So I know the syntax
  193. 7:23is correct. Everything else is
  194. 7:25untouched. Now our entry rule is also
  195. 7:29saying that the value of Williams R must
  196. 7:31be below minus 80. For a short position
  197. 7:34it says it needs to be above minus20. I
  198. 7:37also like these little comments that it
  199. 7:39added. Now as for the position sizing
  200. 7:42it's using the market order for entry.
  201. 7:45The surplus is the current SMA 50 which
  202. 7:48is exactly what we asked. And as for the
  203. 7:50quantity, it is risking 3% which is
  204. 7:52exactly what I asked and it is
  205. 7:55submitting the buy order with the exact
  206. 7:57correct syntax of Jesse. Now as for the
  207. 8:00short position, it's doing the exact
  208. 8:01thing except that instead of using the
  209. 8:04selfby variable for submitting the buy
  210. 8:07order in Jesse, we use self.ell. And
  211. 8:10again the first parameter is the
  212. 8:12quantity of the order and the second one
  213. 8:13is the entry price. We're also saying
  214. 8:15once the position is opened if it's long
  215. 8:17position the stop loss is going to be
  216. 8:20the quantity of the current position and
  217. 8:22the price is going to be the current SMA
  218. 8:2650. As for the take profit we're using
  219. 8:29again the quantity of the current
  220. 8:31position and the price of it is being
  221. 8:33the highest high which again this is the
  222. 8:36definition of it. So we're getting the
  223. 8:38last 30 candles here but only their high
  224. 8:42price which has index of three and we're
  225. 8:44getting the max value of it and if it's
  226. 8:46a short position we do just the
  227. 8:48opposite. Now we're also saying how to
  228. 8:50update the position. So assuming we do
  229. 8:52have an open position now we're saying
  230. 8:54if it's a long position and the rules
  231. 8:56inside the shoot short function are now
  232. 8:58true liquidate the current position and
  233. 9:02if it's vice versa do the opposite. And
  234. 9:05if it's the opposite, again, liquidate
  235. 9:07the position. So, this seems actually
  236. 9:09perfect. I don't think there's going to
  237. 9:10be any errors. So, let's copy the name
  238. 9:12of the strategy. Go back to Jesse and
  239. 9:15look up the name of the strategy here.
  240. 9:17All right. So, if you don't see it here,
  241. 9:19just give it a refresh. All right. So,
  242. 9:20it seems like once we ask the LLM to add
  243. 9:23the Williams percentage R indicator to
  244. 9:26the strategy, it also changed the name
  245. 9:28of it. So, now I could go back and run
  246. 9:30it with the previous name. And this is
  247. 9:32going to behind the scene change the
  248. 9:34name to what it used to be without any
  249. 9:36errors. Or we could create a new
  250. 9:38strategy with this name because I I
  251. 9:40think this name is actually better. So
  252. 9:42let's go back to Jesse. Create a new
  253. 9:44strategy with this name. Go back here.
  254. 9:48Actually, let's look this up first. Copy
  255. 9:50the whole thing and paste it here. So
  256. 9:54now here I should be able to look it up.
  257. 9:57ADX Williams strategy.
  258. 10:00Let's change the time frame to 15 and
  259. 10:03the symbol into BTC UC. The exchange is
  260. 10:07Binance perpetual futures.
  261. 10:09As for the duration, I'm going to do
  262. 10:11this. So, let's begin since 2021
  263. 10:15up until
  264. 10:172022
  265. 10:19and the debug mode should be off. I do
  266. 10:23want to see the interactive charts. So,
  267. 10:25let's leave this on. I want the fast
  268. 10:27mode to be on and also the benchmark
  269. 10:30feature. So, let's run this. Now, I'm
  270. 10:33going to add another one and change the
  271. 10:34duration to begin since 2022 up until
  272. 10:372023
  273. 10:39and then again
  274. 10:42since 2023 up until 2024.
  275. 10:45And then since 2024 up until 2025
  276. 10:49and one last time since the beginning of
  277. 10:522025
  278. 10:54up until just a few days ago. So that
  279. 10:57would be like the 12th of the month.
  280. 11:01So let's start this one too. All right.
  281. 11:03So if I go to the benchmark page, I can
  282. 11:06see all the values simultaneously.
  283. 11:08All right. So I really like these
  284. 11:10numbers. So check this out. The sharp
  285. 11:12ratio is 1.9 for 2021. It is two for
  286. 11:172022, 1.7 in 2023, 1.2 in 2025, and 1.1
  287. 11:25in 2025. So let's take a look at the
  288. 11:29equity curve. All right, so this looks
  289. 11:31fantastic by the way because if we
  290. 11:34consider the draw down, it is minus 6%.
  291. 11:37So that's crazy. But it also allows us
  292. 11:40to add to the size of the position. So
  293. 11:42this panel number that you see here, you
  294. 11:45might think that's nothing. Well, we can
  295. 11:47easily multiply the size of our
  296. 11:49position. So let's go back and do that.
  297. 11:51So I'm going to go to go long
  298. 11:55and multiply my quantity by five.
  299. 12:00And also do the same thing for my short
  300. 12:02positions.
  301. 12:04So let's go back to Jesse. I could rerun
  302. 12:06this one by one or I could simply go to
  303. 12:10the benchmark page and rerun all of them
  304. 12:12at the same time. All right, so check
  305. 12:14this out. Now the equity curve of our
  306. 12:16strategy is clearly beating the market
  307. 12:20in 2022. It also did the same thing. It
  308. 12:23looks fantastic.
  309. 12:25And again, just check out the draw down.
  310. 12:27So with minus 25 even though the market
  311. 12:30lost nearly 70%.
  312. 12:33We made 210%.
  313. 12:35The win rate would have been 60% the
  314. 12:38sharp would have been near two and the
  315. 12:40average holding time of the positions is
  316. 12:42neared 8 hours which is really great
  317. 12:44considering how hard it is to watch your
  318. 12:47strategy do something and then maybe
  319. 12:49lose at the end which makes it really
  320. 12:50difficult to continue with the whole
  321. 12:52trading. All right. On 2023,
  322. 12:56this is our equity curve. We did not
  323. 12:58beat the market, but we did end very
  324. 13:00near. And I don't know the max of the
  325. 13:03benchmark, which in this case is BTC UC,
  326. 13:07but I still this equity curve looks fine
  327. 13:09to me. In 2024,
  328. 13:12we did beat the market up until here
  329. 13:14until the price just went on a hike in
  330. 13:16here. But overall, this equity curve
  331. 13:18looks really good to me. And the max is
  332. 13:20only minus 20%. So you could say we
  333. 13:23could add even more to the size of the
  334. 13:25position in this year. And if we did
  335. 13:28that, we would have beaten the market
  336. 13:30here. But the thing is, you never know,
  337. 13:32right? Like this could have been also a
  338. 13:34bad year. So you always want to be
  339. 13:36careful not to add too much to the size
  340. 13:38of your positions. Now in 2025, we did
  341. 13:41end up beating the market. In the
  342. 13:43beginning of it, we didn't do great, but
  343. 13:45we still didn't lose much. And that's
  344. 13:47really good for me because because the
  345. 13:49beginning of this year actually was
  346. 13:51really bad on most of strategies that I
  347. 13:53know. And the fact that this one isn't
  348. 13:55losing much, I consider that a win. But
  349. 13:58if you do end up trading something like
  350. 14:00this, please remember that, you know,
  351. 14:02for even a few months, you may have been
  352. 14:04in a loss. It wouldn't have been a big
  353. 14:06loss, but still a loss. And that's going
  354. 14:09to be really difficult from a psychology
  355. 14:11point. So just remember that side of
  356. 14:13trading is still difficult even if you
  357. 14:15use an algo like this one. Now, I do
  358. 14:17want to point this that because I added
  359. 14:20to the size of my position and multiply
  360. 14:21it by five. If you are running this back
  361. 14:24test yourself, you do need to make sure
  362. 14:26to go to the settings, find the exchange
  363. 14:29that you're running the back test on,
  364. 14:30and increase the leverage number. Now,
  365. 14:32in here, it is set to 100 because of
  366. 14:34another strategy that I was using. But
  367. 14:36in this one, we don't need it to be this
  368. 14:38high. We could use a number such as five
  369. 14:40or six would be enough. And also because
  370. 14:43we are using market orders in this
  371. 14:45strategy, if you want to be careful and
  372. 14:47consider the slippage value, which may
  373. 14:49not be really important on an exchange
  374. 14:51such as Binance, but in anyways, if you
  375. 14:53want to do that, maybe just increase the
  376. 14:55trading fees by a number such as this,
  377. 14:57so that it would be more close to the
  378. 14:59actual trading results that you will get
  379. 15:01with this strategy. Now, let's do one
  380. 15:03more thing. I want to run another back
  381. 15:04test since the beginning of 2021 up
  382. 15:08until this stage. So we can see the
  383. 15:10total equity curve.
  384. 15:15So while that's going, I want to quickly
  385. 15:16remind you guys about Apex Omni, which
  386. 15:18is my favorite deck made by the team
  387. 15:21behind Bybit. It has low trading fees,
  388. 15:23instant order execution, and of course,
  389. 15:25no KYC whatsoever. If you're going to
  390. 15:28check him out, please consider using our
  391. 15:29link, which not only will give you
  392. 15:31trading fee discounts, but it will also
  393. 15:33support me in order to make more videos
  394. 15:35like this. All right, so check this out.
  395. 15:36We finished the back test for more than
  396. 15:39four years in near 100 seconds and we
  397. 15:43ended up making 4,400%
  398. 15:45in P&L. So assuming we started with
  399. 15:4810,000 in trading capital, we would have
  400. 15:50finished with nearly half a million. The
  401. 15:52max lodon was minus 30. The win rate was
  402. 15:5561%. The sharp ratio was 1.66 which is
  403. 15:59absolutely amazing over this long period
  404. 16:02of time. and our average holding time
  405. 16:04would have been about 14 hours. All
  406. 16:06right, so this looks really good. Now, I
  407. 16:08also want to show you guys something
  408. 16:09else. So, let's take a look at the
  409. 16:11interactive charts which shows us the
  410. 16:14trades that the strategy took. So, here
  411. 16:16you can see the example of a losing
  412. 16:18trade. So, it opened a long position,
  413. 16:20but it had to open it right here. And
  414. 16:23here is an example of a winning trade.
  415. 16:25So, it would have shorted in here and
  416. 16:28closed the position in here. So I'm
  417. 16:30guessing this would have been the exact
  418. 16:32price because this was the lowest low
  419. 16:34value. We can also check out another
  420. 16:36one. So here we would have gone long and
  421. 16:40closed it in here. Again, this highest
  422. 16:43high would have been the takerit. Now we
  423. 16:45could also do something really cool. We
  424. 16:47could also see the values of the
  425. 16:48indicator while this trade was taken. So
  426. 16:51I went back to JCGPT and I simply said
  427. 16:53add indicator values to the interactive
  428. 16:55chart so I can see them. and it gave me
  429. 16:58the new code, but I just want this part.
  430. 17:01So, let's copy it. Go back to the code
  431. 17:05and add it here. Now, by the way, this
  432. 17:07watch list that it added here is really
  433. 17:09useful for live trading, but it has no
  434. 17:12use case in back testing. All right, so
  435. 17:14let's go back to our editor
  436. 17:16and paste it here. Now, in case you're
  437. 17:18not familiar with it, this is the syntax
  438. 17:19we use for displaying the indicator
  439. 17:22values to the chart. You can check it
  440. 17:23out on our documentation or watch my
  441. 17:25previous videos about it. So, but in
  442. 17:27this case, we just got it from Jess GPT.
  443. 17:30And if I go back and rerun this one more
  444. 17:32time, but just so that it would be
  445. 17:34quicker, let's run this one.
  446. 17:38All right. So, we're getting an error.
  447. 17:39It's saying that there's no attribute
  448. 17:41with this name. So, let's go back.
  449. 17:45And yeah, we don't have this. We have
  450. 17:47this one. Okay. So, this one also seems
  451. 17:50to be wrong. So, let's All right. So, it
  452. 17:53didn't get the names of this correct,
  453. 17:55but it's not that bad. So, let's just
  454. 17:57manually change them.
  455. 18:04Okay. So, actually, I'm guessing this is
  456. 18:06happening because I didn't copy the
  457. 18:08whole thing. You know what? Let's
  458. 18:09actually go back cuz I want to see if it
  459. 18:13also changed the names of these in here.
  460. 18:20So yeah, it did change the names of
  461. 18:22those variables. So if I did copy the
  462. 18:24whole thing from here, it would have
  463. 18:26worked. But that's okay. Let's just
  464. 18:28change this manually
  465. 18:32and we should be good to go. So let's go
  466. 18:34back to Jesse and run it one more time.
  467. 18:39All right. So let's open the charts. All
  468. 18:41right. So let's go to this one for
  469. 18:42example, which is a losing trade. So you
  470. 18:44see we opened it here and closed it
  471. 18:46here. And you can also see the values.
  472. 18:49So yes, the ADX was above the threshold
  473. 18:51which in here is red. And the DI value
  474. 18:54was also like this. So because this DI
  475. 18:58plus value was above the DI minus which
  476. 19:01is this red line in here, we opened the
  477. 19:03long position and the William R was also
  478. 19:06oversold. So all the entry rules were
  479. 19:09met in here and you can clearly see
  480. 19:11that. But still this was a losing trade
  481. 19:13and you could use this scenario here to
  482. 19:17maybe add another filter so that this
  483. 19:19losing trade wouldn't have been taken.
  484. 19:21But if you are going to do that be very
  485. 19:23careful because that's basically the
  486. 19:25recipe for overfitting. Now you could do
  487. 19:28it a little bit and that's fine but
  488. 19:30overdoing it is not okay. Also when you
  489. 19:32do something to not take a losing trade
  490. 19:35you're also going to not take some of
  491. 19:36your winning trades. So it's not a
  492. 19:38perfect system. Now let's check out a
  493. 19:40winning trade. So let's double click on
  494. 19:43this to reset it. All right. So we took
  495. 19:45this right here. The ADX was clearly
  496. 19:48above the threshold and the DI plus
  497. 19:51value was below the DI minus and that's
  498. 19:54because this was a short position and
  499. 19:56the William R was also overbought. So
  500. 20:00all the integer rules were met at this
  501. 20:02point. Now I am going to submit this
  502. 20:04strategy to our strategies index page
  503. 20:07which allows you to see the results of
  504. 20:09it for other symbols and also time
  505. 20:12periods or time frames. You can also
  506. 20:14download the code for previous
  507. 20:15strategies that I have created. So I
  508. 20:17actually really like the results of this
  509. 20:19strategy and I think I'm going to keep
  510. 20:20working on it. I may even create a
  511. 20:22premium version of it and again submit
  512. 20:24it to our strategies page. Now before I
  513. 20:26leave, we're going to have a giveaway. A
  514. 20:28random person who likes this video, post
  515. 20:29a comment and subscribes to the channel
  516. 20:31is going to win 1 million bank token.
  517. 20:33All right, let's pick the winner from
  518. 20:34the previous video and the winner is
  519. 20:36Antune Line. I hope I didn't butcher
  520. 20:39your name. Thank you so much for your
  521. 20:40comment. Please reach out to me so that
  522. 20:42I can send you your bank tokens. Thank
  523. 20:44you guys for watching and I'll see you
  524. 20:45in the next one.
  525. 20:51[Music]
  526. 20:52[Applause]
  527. 20:54[Music]

About this transcript

This page contains the full transcript of GPT: ADX scalping strategy in Python makes 4479% by Algo-trading with Saleh, generated from the public captions YouTube serves with the video. The transcript has 3,880 words across 527 segments, with the original timestamps preserved so you can click any line to jump to that moment in the embedded player.

What you can do with it

Use the transcript to take notes, quote the speaker, build a study guide, generate a summary with ChatGPT or Claude via the YouTube Summary tool, or export it as a timed subtitle file with YouTube to SRT. You can also re-open it in the transcriber to translate the transcript into 100+ languages.

Free YouTube transcript tool

YouTube2Text is a free YouTube transcript generator — no signup, no daily limit. Paste any YouTube link and get the full transcript instantly, with timestamps, click-to-jump, translation to 100+ languages, AI prompts for ChatGPT, Claude, and Gemini, and exports to TXT, SRT, VTT, or Markdown.