ComfyUI Course 1-10

The last two videos were generated in the LTX-2 Image to Video workflow, the text of the woman's voice is written in the prompt and the woman's movements are described. The voice is not clear, robotic and the image quality in the video is worse than in Wan2.2, but it generates faster.
Sometimes the woman does not communicate with her voice. LTX previously had such shortcomings with video quality.
LTX-2 now has the ability to download images and audio.

This video is on LTX-2 Image to Video with Custom Audio, it turned out quite well. Video 704x1280 6 seconds per image, audio was generated in the cloud for 5 minutes (24 GB Vram), on PC it will take much longer to generate if the video card is weaker.
When generating this workflow on PC I had an error.

1. Qwen3-TTS CustomVoice    Workflow screenshot
We're using the Ryan preset for stable narration, then saving straight to MP3. Pretty clean, right?

2. Qwen3-TTS VoiceDesign    Workflow screenshot
What's up, I'm Pixaroma. In this workflow we design a custom voice. Instead of picking a preset speaker, you describe it.

2. Qwen3-TTS VoiceDesign    Workflow screenshot
I am sorry, that was funnier than it should be.

2. Qwen3-TTS VoiceDesign    Workflow screenshot
I thought I was ready, but I was wrong.

2. Qwen3-TTS VoiceDesign    Workflow screenshot
You promised. You lied. You mother Beeeep...

2. Qwen3-TTS VoiceDesign    Workflow screenshot
Do you hear that, behind us?

2. Qwen3-TTS VoiceDesign    Workflow screenshot
In a world where nothing makes sense, one choice changes everything.

2. Qwen3-TTS VoiceDesign    Workflow screenshot
Team, eyes up. We move in ten seconds.

2. Qwen3-TTS VoiceDesign    Workflow screenshot
Muhahaha, the plan is flawless, mostly.

2. Qwen3-TTS VoiceDesign    Workflow screenshot
Hi friend, want to try something yummy today?

2. Qwen3-TTS VoiceDesign    Workflow screenshot
I do not like it. I do not trust it.

2. Qwen3-TTS VoiceDesign    Workflow screenshot
Shh, listen, the stars are talking tonight.

2. Qwen3-TTS VoiceDesign    Workflow screenshot
Okay okay okay, we run, then we hide, then snacks!

2. Qwen3-TTS VoiceDesign    Workflow screenshot
Come closer. I want to tell you something.

2. Qwen3-TTS VoiceDesign    Workflow screenshot
Good morning, you are listening to Starwave, stay with us.

2. Qwen3-TTS VoiceDesign    Workflow screenshot
Fresh today, priced right, come in and save.

2. Qwen3-TTS VoiceDesign    Workflow screenshot
Let your shoulders drop, and let your thoughts pass by.

2. Qwen3-TTS VoiceDesign    Workflow screenshot
Listen to that. Soft. Clean. Perfect.

2. Qwen3-TTS VoiceDesign    Workflow screenshot
I am having so much fun with this workflow. Are you ready for the next one?

3. Qwen3-TTS VoiceClone    Workflow screenshot
Reference Audio Text (Must Match Voice Sample Audio):
Hey, I'm AI generated. Be honest, do you like my voice and does it feel real?
Speech Text:
Welcome to Pixaroma Radio. This is Alison speaking. Today we're testing a cloned female voice inside ComfyUI. Pretty cool, right?

3. Qwen3-TTS VoiceClone    Workflow screenshot
Reference Audio Text (Must Match Voice Sample Audio):
I am having so much fun with this workflow. Are you ready for the next one?
Speech Text:
Welcome to Pixaroma Radio. This is Alison speaking. Today we're testing a cloned female voice inside ComfyUI. Pretty cool, right?

4. Qwen3-TTS VoiceClone + SaveVoice    Workflow screenshot
Reference Audio Text (Must Match Voice Sample Audio):
Hey, I'm Al generated. Be honest, do you like my voice and does it feel real?
Speech Text:
Welcome to Pixaroma Radio. This is Alison speaking. Today we're testing a cloned female voice inside ComfyUI. Pretty cool, right?

5. Qwen3-TTS VoiceDesign + SaveVoice    Workflow screenshot
What's up, I'm Pixaroma. In this workflow we design a custom voice. Instead of picking a preset speaker, you describe it.

6. Qwen3-TTS VoiceClone + Load A Previous Saved Voice    Workflow screenshot
Welcome to Pixaroma Radio. Today we're testing a cloned voice inside ComfyUI. Pretty cool, right?

6. Qwen3-TTS VoiceClone + Load A Previous Saved Voice    Workflow screenshot
Welcome to Pixaroma Radio. Today we're testing a cloned voice inside ComfyUI. Pretty cool, right?

7. Qwen3-TTS VoiceClone + Load Saved Multi Voice + Dialogue    Workflow screenshot
man: Hey, you there?
woman: Yeah, I'm here, what are we testing?
man: A clean TTS workflow in ComfyUI
woman: Nice, voice design or cloned voice?
man: Cloned voice for consistency
woman: Love it!

8. Qwen3-TTS VoiceDesign + Dialogue    Workflow screenshot
man: Hey, you there?
woman: Yeah, I'm here, what are we testing?
man: A clean TTS workflow in ComfyUI
woman: Nice, voice design or cloned voice?
man: Cloned voice for consistency
woman: Love it!

1. Fish S2 Voice Clone TTS    Workflow screenshot
[happy] Hey, this is Pixaroma, and [laughing] okay, this is already making me way too happy. [giggle] There is just something so fun and exciting about all of this. [Inhale] So come on, let us enjoy every second together. [crowd laughing] [background laughter]

2. Fish S2 TTS    Workflow screenshot
[A cheerful female voice with a joking, playful tone] [happy] I clicked one button, everything broke, and for a second .. [pause]
I just stared at the screen! [pause], [laughing] [laughing] Honestly, it was kind of impressive.

3. Fish S2 Multi-Speaker TTS    Workflow screenshot
[speaker_1]: [excited] So, what are we doing today?
[speaker_2]: [professional broadcast tone] Something simple, but really useful.
[speaker_1]: [happy] Nice, I like the sound of that
[speaker_2]: [inhale]Then let us get started [laughing][chuckle].