YouTube2Text

وداعاً ElevenLabs! أصوات ذكاء اصطناعي مجانية وغير محدودة — Transcript

by هفيدك تك - Hafedktech · 1,830 words · 274 segments · language en · Watch on YouTube

Full transcript

  1. 0:00If you make the coolest video in the
  2. 0:02world with amazing visuals and
  3. 0:03top-notch editing, but the voiceover
  4. 0:05sounds like a stiff robot or has poor
  5. 0:07quality, your video was dead before it
  6. 0:09was even born. Of course, we all know
  7. 0:12the "Adam" voice from ElevenLabs. The
  8. 0:14calm, composed voice we hear in most.
  9. 0:15AI videos and stories. The problem is
  10. 0:18that using it consumes your credits.
  11. 0:20And if they run out, you have to pay in
  12. 0:22dollars to continue. So, what if I told
  13. 0:24you that we can get that exact same
  14. 0:26voice? With the same tone and the same
  15. 0:29power, completely free and unlimited on
  16. 0:31your own device. We will turn your
  17. 0:33computer into a professional radio
  18. 0:35station that works offline with no
  19. 0:37usage limits. We’ll learn how to
  20. 0:39clone your voice and how to make AI
  21. 0:41speak with real emotions. All of this
  22. 0:43with just the click of a button. Get
  23. 0:45your headphones ready and focus with me
  24. 0:46, because from today on, your videos
  25. 0:48will have a voice that speaks for you.
  26. 0:50The first model we’ll use on the
  27. 0:52Pinokio program is Ultimate TTS Studio
  28. 0:55Pro. It’s a very powerful model with
  29. 0:57many features we’ll talk about. If
  30. 1:00you’ve noticed in ElevenLabs—if we
  31. 1:02open ElevenLabs, there’s a very
  32. 1:05famous voice called Adam that you hear
  33. 1:07a lot in AI-made videos, shorts, and
  34. 1:09long videos; it’s the voice called
  35. 1:12Adam from ElevenLabs, if you’ve heard
  36. 1:14it.
  37. 1:17It's naturally very well-known. Now, if
  38. 1:19we go to Ultimate TTS Studio. Adam is
  39. 1:22there too, and it’s completely free
  40. 1:24and "ultimate." And you can play with
  41. 1:27the voices as much as you like. For
  42. 1:29example, here is Adam TTS Studio. And
  43. 1:32if you generate speech, And also, quite
  44. 1:38simply, you can go in here to the speed
  45. 1:40settings. You can increase the speed,
  46. 1:43or add other effects here. Like bass,
  47. 1:46mid, and treble. You can adjust
  48. 1:48everything and see how the voice suits
  49. 1:51you. Alright, so how do you use this
  50. 1:54model or how do you get it? First thing
  51. 1:56, of course, let’s open Pinokio first
  52. 1:58. We’ll go to the "Community" tab.
  53. 2:00And go to "TTS" here. Click on TTS and
  54. 2:03scroll down. You will find something
  55. 2:05called Ultimate TTS Studio. Make sure
  56. 2:07it says "Featured" next to it, alright.
  57. 2:10So it’s the primary one featured by
  58. 2:12the Pinokio Factory. You’ll click on
  59. 2:14it and install it quite simply, alright
  60. 2:16. You’ll hit install, and you’ll
  61. 2:18install the latest version; I, of
  62. 2:19course, have it installed already. So
  63. 2:21let’s go back and open it again. What
  64. 2:22is the next step to run, for example,
  65. 2:25the Adam voice or the 32 voices
  66. 2:28available on the model called Kokoro
  67. 2:31TTS? You will go here to the word "
  68. 2:33Kokoro TTS" and click "Load." It will
  69. 2:35tell you "Loaded." And here, of course,
  70. 2:37you can write the text you want it to
  71. 2:38generate. And naturally, it only
  72. 2:40supports English. Then scroll down like
  73. 2:42this, okay. You’ll find there are 32
  74. 2:44supported voices here with the country
  75. 2:46next to them. So, Adam here speaks in
  76. 2:49English US. You have Nova here, you
  77. 2:51have Sky. You can listen to any other
  78. 2:53voice. You have Nicola. You can hit "
  79. 2:55Generate Speech." It’s processing,
  80. 2:57exactly. It will say that text. T.
  81. 3:03Like this, for example, this is
  82. 3:05Nicola's voice; you have, for instance,
  83. 3:07another voice called George.
  84. 3:13This is another different voice, for
  85. 3:14example. And as I said, you can adjust
  86. 3:16anything. I also want to draw your
  87. 3:18attention to something. The size of
  88. 3:20Ultimate TTS Studio is 17.5 gigabytes.
  89. 3:23Alright. This is approximately the
  90. 3:26space for installing just the Core TTS
  91. 3:28model built into Ultimate TTS Studio.
  92. 3:31Because there are many models here
  93. 3:32under TTS model management. You can
  94. 3:34choose any model and work with it. For
  95. 3:36example, I'm telling you now that you
  96. 3:38are currently working with Core TTS.
  97. 3:40Because there is Adam's voice and
  98. 3:41several other voices in English. There
  99. 3:43are other models you can try out. Load
  100. 3:45this model and see how it works. Load
  101. 3:47this model or choose any of these
  102. 3:49models. To see if it gives you the
  103. 3:51voice you want or not. There are, of
  104. 3:54course, many options. And if you find
  105. 3:55that the gigabytes have increased a bit
  106. 3:56for you. You can click on Clean Temp
  107. 3:59Files. To delete the temporary files.
  108. 4:02That's if you feel your storage space
  109. 4:05has grown too much. Alright. Now,
  110. 4:07someone might tell me, "No, I'm not
  111. 4:09going to download those 17.5 gigabytes.
  112. 4:11" There is a very good alternative.
  113. 4:13It's a website called SpeechMa. This
  114. 4:15SpeechMa website provides you with many
  115. 4:17voices in multiple languages. And it is
  116. 4:20free so far. Alright. For example, you
  117. 4:23can look at my voice, for instance.
  118. 4:27You have, for example, this child's
  119. 4:30voice in English. You can use it to
  120. 4:31make illustrated stories for foreign
  121. 4:33content, for example. Here is Andrew
  122. 4:35and so on. And it's also very special.
  123. 4:38If you want to create voices in Arabic,
  124. 4:40there is Arabic here quite normally.
  125. 4:42Female and male voices, for example,
  126. 4:45Hamdan.
  127. 4:46Welcome to SpeechMa.
  128. 4:48Welcome to SpeechMa.
  129. 4:51We can test, for example, by choosing
  130. 4:53any voice from here, like Ismail.
  131. 4:56Welcome to SpeechMa, where you can...
  132. 4:59I clicked on Ismail, for example; I
  133. 5:00want to write something and generate it
  134. 5:02. It might not be the best, but this is
  135. 5:05what is available for free. You do the
  136. 5:07captcha, click generate audio, and
  137. 5:08after it's produced, you can click play
  138. 5:10.
  139. 5:11I am currently speaking with Ismail's
  140. 5:13voice and testing it with you.
  141. 5:15The voice is obviously not the best for
  142. 5:17Arabic either. But there is also
  143. 5:19another website. The better version of
  144. 5:22SpeechMa is SpeechNa. You have, for
  145. 5:24example, their voice studio. They say
  146. 5:27that there are 30 voices available,
  147. 5:28okay. And they tell you these voices
  148. 5:30can speak all these languages, okay.
  149. 5:32For example, Marcus's voice.
  150. 5:38But the thing is that this website now
  151. 5:40has pricing. It gives you 2,000 audio
  152. 5:43credits. But it's not unlimited like
  153. 5:46Ultimate TTS Studio. These are also
  154. 5:48online alternatives that you can use.
  155. 5:50The second application we have in the
  156. 5:53Pinokio program is Zonos. Zonos. This
  157. 5:55is very powerful. You can do two very
  158. 5:57important things with it. One is to
  159. 5:59clone your voice. But of course, only
  160. 6:02in English, unfortunately. Because it's
  161. 6:04not the best for Arabic. And you can
  162. 6:06also control the emotions of the
  163. 6:09voiceover you are creating. So now I
  164. 6:11have put in text to synthesize. It
  165. 6:14expresses this speech through emotions
  166. 6:18or feelings. Alright. And here in the
  167. 6:20language code, you choose, for example,
  168. 6:23EN United States. And there are several
  169. 6:25EN options you can try. It also has
  170. 6:27about seven AI voices in English. And
  171. 6:31other languages like French and so on.
  172. 6:33But when I tried it in Arabic, it
  173. 6:34wasn't the best, unfortunately. You can
  174. 6:36adjust the speaker's speed. It will
  175. 6:39speak quickly. Speak slowly, and so on.
  176. 6:42This is the audio after I gave it the
  177. 6:44text here. This application and the
  178. 6:54Zonos model are very good at
  179. 6:57controlling emotions. Here, for example
  180. 7:00, it spoke with emotion. It narrated
  181. 7:02this text with emotion, not like a
  182. 7:04robotic AI. And here, if you go to
  183. 7:06Advanced Parameters, you can control
  184. 7:09happiness, sadness, and fear. For
  185. 7:12instance, I can reduce happiness,
  186. 7:14increase sadness, or increase fear.
  187. 7:18Because it is talking here about
  188. 7:19feeling depressed. And about sitting
  189. 7:21with his own thoughts and such. And I
  190. 7:23press Generate Audio. Here, for example
  191. 7:35, is the output after adjusting the
  192. 7:38emotions. The idea with this
  193. 7:40application is that it chooses the
  194. 7:42voices for you. The problem is, for
  195. 7:45example, you can't specify if you want
  196. 7:46a male or female voice. But of course,
  197. 7:49Ultimate TTS Studio gives you options
  198. 7:51to control whether it's male or female.
  199. 7:53You can also clone your voice in
  200. 7:57English. For example, I tried it in
  201. 7:59English. You go here to Optional
  202. 8:01Speaker Audio. If you want to copy
  203. 8:04someone's voice and use it in the Zonos
  204. 8:07program. You can go here and provide a
  205. 8:09sample of your voice. Here, for example
  206. 8:11, is my English voice, the introduction
  207. 8:12. Upload. After I uploaded my voice to
  208. 8:17the Zonos program to clone or copy it.
  209. 8:19And I put in text. Different from the
  210. 8:21text we chose. And I pressed Generate
  211. 8:23Audio. If you hear my original voice,
  212. 8:26the introduction sample upload marker.
  213. 8:31Okay. This is my original voice in
  214. 8:32English. And this is the voice cloned
  215. 8:35by the Zonos program. It's the same
  216. 8:41tone but doesn't quite sound like me
  217. 8:43exactly. It's not exactly my voice. It
  218. 8:45might be my voice but with an
  219. 8:47Italian-Indian accent a bit. Perhaps
  220. 8:50because I didn't record the English
  221. 8:52voice in the best way. Meaning the
  222. 8:54accent might not be the best. So the
  223. 8:56audio came out with this quality. But
  224. 8:57it's high quality, of course, free, and
  225. 8:59in ultimate format. And this is
  226. 9:01provided to you by the Zonos program.
  227. 9:02You can also clone your voice. But
  228. 9:04unfortunately, only in English. If we
  229. 9:06also want to try Zonos in Arabic. Let's
  230. 9:08go, for example, to the language code
  231. 9:09here. And go up and press AR and write.
  232. 9:12Write, for example, anything here.
  233. 9:13Remove my clone. Write anything here,
  234. 9:16for example, and tell it to generate.
  235. 9:18If you notice, we go here to the
  236. 9:19terminal. Okay. It will give me an
  237. 9:21error. Why? Because unfortunately, it
  238. 9:24cannot read Arabic. Okay. Generate
  239. 9:26Audio error as well. It cannot read
  240. 9:28Arabic, unfortunately, in the language
  241. 9:30code. And if I go back to English, for
  242. 9:33example. And I told it to generate and
  243. 9:35went here to the terminal. Okay. You
  244. 9:37will find here "failed to load voice AR
  245. 9:39". There is no voice for AR at all.
  246. 9:40When I changed it to English, EN. It
  247. 9:42will start producing something. And
  248. 9:43it's doing an infinite loop. Because it
  249. 9:44doesn't know how to read Arabic. Okay.
  250. 9:46So we will need to stop this. Okay.
  251. 9:49Because unfortunately, it does not
  252. 9:51support the Arabic language. And with
  253. 9:53that, we have reached the end of this
  254. 9:54video. I hope you found it useful. We
  255. 9:56talked about Ultima TTS Studio Pro. And
  256. 9:59we talked about the SpeechMa website.
  257. 10:00And also about Zonos. All are strong
  258. 10:03free alternatives to ElevenLabs. They
  259. 10:06give you the same quality and are
  260. 10:08ultimate. You can start your foreign
  261. 10:10content creation with them. Opening a
  262. 10:12new door for your livelihood. And you
  263. 10:13can earn dollars from it, God willing.
  264. 10:15In the coming videos, we will try to
  265. 10:17look for things in Arabic. That are
  266. 10:19also as good as SpeechMa and free. And
  267. 10:21we will continue the series on creating
  268. 10:23content with AI for free. Without
  269. 10:26limits locally or on any free site. If
  270. 10:30you liked the video, don't forget to
  271. 10:31like and subscribe. And leave us a
  272. 10:33comment on what other video you'd like
  273. 10:34to see from us. Peace be upon you and
  274. 10:36God's mercy and blessings.

About this transcript

This page contains the full transcript of وداعاً ElevenLabs! أصوات ذكاء اصطناعي مجانية وغير محدودة by هفيدك تك - Hafedktech, generated from the public captions YouTube serves with the video. The transcript has 1,830 words across 274 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 choose a caption track available on the video.

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, caption language selection, AI prompts for ChatGPT, Claude, and Gemini, and exports to TXT, SRT, VTT, or Markdown.