وداعاً ElevenLabs! أصوات ذكاء اصطناعي مجانية وغير محدودة — Transcript
Full transcript
- 0:00If you make the coolest video in the
- 0:02world with amazing visuals and
- 0:03top-notch editing, but the voiceover
- 0:05sounds like a stiff robot or has poor
- 0:07quality, your video was dead before it
- 0:09was even born. Of course, we all know
- 0:12the "Adam" voice from ElevenLabs. The
- 0:14calm, composed voice we hear in most.
- 0:15AI videos and stories. The problem is
- 0:18that using it consumes your credits.
- 0:20And if they run out, you have to pay in
- 0:22dollars to continue. So, what if I told
- 0:24you that we can get that exact same
- 0:26voice? With the same tone and the same
- 0:29power, completely free and unlimited on
- 0:31your own device. We will turn your
- 0:33computer into a professional radio
- 0:35station that works offline with no
- 0:37usage limits. We’ll learn how to
- 0:39clone your voice and how to make AI
- 0:41speak with real emotions. All of this
- 0:43with just the click of a button. Get
- 0:45your headphones ready and focus with me
- 0:46, because from today on, your videos
- 0:48will have a voice that speaks for you.
- 0:50The first model we’ll use on the
- 0:52Pinokio program is Ultimate TTS Studio
- 0:55Pro. It’s a very powerful model with
- 0:57many features we’ll talk about. If
- 1:00you’ve noticed in ElevenLabs—if we
- 1:02open ElevenLabs, there’s a very
- 1:05famous voice called Adam that you hear
- 1:07a lot in AI-made videos, shorts, and
- 1:09long videos; it’s the voice called
- 1:12Adam from ElevenLabs, if you’ve heard
- 1:14it.
- 1:17It's naturally very well-known. Now, if
- 1:19we go to Ultimate TTS Studio. Adam is
- 1:22there too, and it’s completely free
- 1:24and "ultimate." And you can play with
- 1:27the voices as much as you like. For
- 1:29example, here is Adam TTS Studio. And
- 1:32if you generate speech, And also, quite
- 1:38simply, you can go in here to the speed
- 1:40settings. You can increase the speed,
- 1:43or add other effects here. Like bass,
- 1:46mid, and treble. You can adjust
- 1:48everything and see how the voice suits
- 1:51you. Alright, so how do you use this
- 1:54model or how do you get it? First thing
- 1:56, of course, let’s open Pinokio first
- 1:58. We’ll go to the "Community" tab.
- 2:00And go to "TTS" here. Click on TTS and
- 2:03scroll down. You will find something
- 2:05called Ultimate TTS Studio. Make sure
- 2:07it says "Featured" next to it, alright.
- 2:10So it’s the primary one featured by
- 2:12the Pinokio Factory. You’ll click on
- 2:14it and install it quite simply, alright
- 2:16. You’ll hit install, and you’ll
- 2:18install the latest version; I, of
- 2:19course, have it installed already. So
- 2:21let’s go back and open it again. What
- 2:22is the next step to run, for example,
- 2:25the Adam voice or the 32 voices
- 2:28available on the model called Kokoro
- 2:31TTS? You will go here to the word "
- 2:33Kokoro TTS" and click "Load." It will
- 2:35tell you "Loaded." And here, of course,
- 2:37you can write the text you want it to
- 2:38generate. And naturally, it only
- 2:40supports English. Then scroll down like
- 2:42this, okay. You’ll find there are 32
- 2:44supported voices here with the country
- 2:46next to them. So, Adam here speaks in
- 2:49English US. You have Nova here, you
- 2:51have Sky. You can listen to any other
- 2:53voice. You have Nicola. You can hit "
- 2:55Generate Speech." It’s processing,
- 2:57exactly. It will say that text. T.
- 3:03Like this, for example, this is
- 3:05Nicola's voice; you have, for instance,
- 3:07another voice called George.
- 3:13This is another different voice, for
- 3:14example. And as I said, you can adjust
- 3:16anything. I also want to draw your
- 3:18attention to something. The size of
- 3:20Ultimate TTS Studio is 17.5 gigabytes.
- 3:23Alright. This is approximately the
- 3:26space for installing just the Core TTS
- 3:28model built into Ultimate TTS Studio.
- 3:31Because there are many models here
- 3:32under TTS model management. You can
- 3:34choose any model and work with it. For
- 3:36example, I'm telling you now that you
- 3:38are currently working with Core TTS.
- 3:40Because there is Adam's voice and
- 3:41several other voices in English. There
- 3:43are other models you can try out. Load
- 3:45this model and see how it works. Load
- 3:47this model or choose any of these
- 3:49models. To see if it gives you the
- 3:51voice you want or not. There are, of
- 3:54course, many options. And if you find
- 3:55that the gigabytes have increased a bit
- 3:56for you. You can click on Clean Temp
- 3:59Files. To delete the temporary files.
- 4:02That's if you feel your storage space
- 4:05has grown too much. Alright. Now,
- 4:07someone might tell me, "No, I'm not
- 4:09going to download those 17.5 gigabytes.
- 4:11" There is a very good alternative.
- 4:13It's a website called SpeechMa. This
- 4:15SpeechMa website provides you with many
- 4:17voices in multiple languages. And it is
- 4:20free so far. Alright. For example, you
- 4:23can look at my voice, for instance.
- 4:27You have, for example, this child's
- 4:30voice in English. You can use it to
- 4:31make illustrated stories for foreign
- 4:33content, for example. Here is Andrew
- 4:35and so on. And it's also very special.
- 4:38If you want to create voices in Arabic,
- 4:40there is Arabic here quite normally.
- 4:42Female and male voices, for example,
- 4:45Hamdan.
- 4:46Welcome to SpeechMa.
- 4:48Welcome to SpeechMa.
- 4:51We can test, for example, by choosing
- 4:53any voice from here, like Ismail.
- 4:56Welcome to SpeechMa, where you can...
- 4:59I clicked on Ismail, for example; I
- 5:00want to write something and generate it
- 5:02. It might not be the best, but this is
- 5:05what is available for free. You do the
- 5:07captcha, click generate audio, and
- 5:08after it's produced, you can click play
- 5:10.
- 5:11I am currently speaking with Ismail's
- 5:13voice and testing it with you.
- 5:15The voice is obviously not the best for
- 5:17Arabic either. But there is also
- 5:19another website. The better version of
- 5:22SpeechMa is SpeechNa. You have, for
- 5:24example, their voice studio. They say
- 5:27that there are 30 voices available,
- 5:28okay. And they tell you these voices
- 5:30can speak all these languages, okay.
- 5:32For example, Marcus's voice.
- 5:38But the thing is that this website now
- 5:40has pricing. It gives you 2,000 audio
- 5:43credits. But it's not unlimited like
- 5:46Ultimate TTS Studio. These are also
- 5:48online alternatives that you can use.
- 5:50The second application we have in the
- 5:53Pinokio program is Zonos. Zonos. This
- 5:55is very powerful. You can do two very
- 5:57important things with it. One is to
- 5:59clone your voice. But of course, only
- 6:02in English, unfortunately. Because it's
- 6:04not the best for Arabic. And you can
- 6:06also control the emotions of the
- 6:09voiceover you are creating. So now I
- 6:11have put in text to synthesize. It
- 6:14expresses this speech through emotions
- 6:18or feelings. Alright. And here in the
- 6:20language code, you choose, for example,
- 6:23EN United States. And there are several
- 6:25EN options you can try. It also has
- 6:27about seven AI voices in English. And
- 6:31other languages like French and so on.
- 6:33But when I tried it in Arabic, it
- 6:34wasn't the best, unfortunately. You can
- 6:36adjust the speaker's speed. It will
- 6:39speak quickly. Speak slowly, and so on.
- 6:42This is the audio after I gave it the
- 6:44text here. This application and the
- 6:54Zonos model are very good at
- 6:57controlling emotions. Here, for example
- 7:00, it spoke with emotion. It narrated
- 7:02this text with emotion, not like a
- 7:04robotic AI. And here, if you go to
- 7:06Advanced Parameters, you can control
- 7:09happiness, sadness, and fear. For
- 7:12instance, I can reduce happiness,
- 7:14increase sadness, or increase fear.
- 7:18Because it is talking here about
- 7:19feeling depressed. And about sitting
- 7:21with his own thoughts and such. And I
- 7:23press Generate Audio. Here, for example
- 7:35, is the output after adjusting the
- 7:38emotions. The idea with this
- 7:40application is that it chooses the
- 7:42voices for you. The problem is, for
- 7:45example, you can't specify if you want
- 7:46a male or female voice. But of course,
- 7:49Ultimate TTS Studio gives you options
- 7:51to control whether it's male or female.
- 7:53You can also clone your voice in
- 7:57English. For example, I tried it in
- 7:59English. You go here to Optional
- 8:01Speaker Audio. If you want to copy
- 8:04someone's voice and use it in the Zonos
- 8:07program. You can go here and provide a
- 8:09sample of your voice. Here, for example
- 8:11, is my English voice, the introduction
- 8:12. Upload. After I uploaded my voice to
- 8:17the Zonos program to clone or copy it.
- 8:19And I put in text. Different from the
- 8:21text we chose. And I pressed Generate
- 8:23Audio. If you hear my original voice,
- 8:26the introduction sample upload marker.
- 8:31Okay. This is my original voice in
- 8:32English. And this is the voice cloned
- 8:35by the Zonos program. It's the same
- 8:41tone but doesn't quite sound like me
- 8:43exactly. It's not exactly my voice. It
- 8:45might be my voice but with an
- 8:47Italian-Indian accent a bit. Perhaps
- 8:50because I didn't record the English
- 8:52voice in the best way. Meaning the
- 8:54accent might not be the best. So the
- 8:56audio came out with this quality. But
- 8:57it's high quality, of course, free, and
- 8:59in ultimate format. And this is
- 9:01provided to you by the Zonos program.
- 9:02You can also clone your voice. But
- 9:04unfortunately, only in English. If we
- 9:06also want to try Zonos in Arabic. Let's
- 9:08go, for example, to the language code
- 9:09here. And go up and press AR and write.
- 9:12Write, for example, anything here.
- 9:13Remove my clone. Write anything here,
- 9:16for example, and tell it to generate.
- 9:18If you notice, we go here to the
- 9:19terminal. Okay. It will give me an
- 9:21error. Why? Because unfortunately, it
- 9:24cannot read Arabic. Okay. Generate
- 9:26Audio error as well. It cannot read
- 9:28Arabic, unfortunately, in the language
- 9:30code. And if I go back to English, for
- 9:33example. And I told it to generate and
- 9:35went here to the terminal. Okay. You
- 9:37will find here "failed to load voice AR
- 9:39". There is no voice for AR at all.
- 9:40When I changed it to English, EN. It
- 9:42will start producing something. And
- 9:43it's doing an infinite loop. Because it
- 9:44doesn't know how to read Arabic. Okay.
- 9:46So we will need to stop this. Okay.
- 9:49Because unfortunately, it does not
- 9:51support the Arabic language. And with
- 9:53that, we have reached the end of this
- 9:54video. I hope you found it useful. We
- 9:56talked about Ultima TTS Studio Pro. And
- 9:59we talked about the SpeechMa website.
- 10:00And also about Zonos. All are strong
- 10:03free alternatives to ElevenLabs. They
- 10:06give you the same quality and are
- 10:08ultimate. You can start your foreign
- 10:10content creation with them. Opening a
- 10:12new door for your livelihood. And you
- 10:13can earn dollars from it, God willing.
- 10:15In the coming videos, we will try to
- 10:17look for things in Arabic. That are
- 10:19also as good as SpeechMa and free. And
- 10:21we will continue the series on creating
- 10:23content with AI for free. Without
- 10:26limits locally or on any free site. If
- 10:30you liked the video, don't forget to
- 10:31like and subscribe. And leave us a
- 10:33comment on what other video you'd like
- 10:34to see from us. Peace be upon you and
- 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.