Make AI Character Videos Fast With 11labs + Midjourney (Full Transcript)

A 10-minute workflow: design a voice in ElevenLabs, generate character visuals in Midjourney, then lip-sync and animate in Hydra.

Download Transcript (DOCX)

Speakers

Add new speaker

[00:00:00] Speaker 1: Today we're going to show you how to use 11labs, Midjourney and Hydra to create incredible videos like this. Welcome Captain Myra Voss. Greetings my friend.

[00:00:10] Speaker 2: Let's start with voice design. Voice design is almost a miracle and it's incredibly simple, it can be complex. This one was as simple as deep, tough, gravelly, legendary cowboy, southern accent. So let's try a little example here.

[00:00:21] Speaker 1: You know there's just something about the way the sun sets over the horizon here in the south.

[00:00:27] Speaker 2: That's really good. I love the way it's slurring and then once you're happy with your voice from voice design, we'll bring it into the TTS playground. We've got our character here, Cowboy, so let's see how that sounds.

[00:00:38] Speaker 1: Hey, this town ain't big enough for the both of us.

[00:00:42] Speaker 2: I'm actually a little bit intimidated by that voice. The next step is visuals, so we're going to head to Midjourney for that. I love the way it uses colours and the depth of field and one thing I love about this is we can edit and scale out, which is quite important when you're putting it to film and lip sync. And then when you bring it into Hydra, once you're happy with your picture, you literally just upload it on the right here. Upload your Eleven Labs voice here.

[00:01:05] Speaker 1: Hey, this town ain't big enough for the both of us. So that whole process took about 10 minutes maximum to get something that sounds amazing, looks amazing and has been animated. I'm blown away that this is all possible.

[00:01:18] Speaker 2: And the source is always in the audio, so go and try out V3 in voice design now.

Summary

A short walkthrough demonstrates how to create an AI-animated character video in about 10 minutes by combining ElevenLabs for voice design and text-to-speech, Midjourney for generating and editing character visuals, and Hydra for uploading the image and audio to produce lip-synced animation. The presenters emphasize starting with a well-designed voice (e.g., a deep, gravelly southern cowboy) and note that the audio is the key source for the final result, encouraging users to try ElevenLabs Voice Design V3.

Copy

Download

Title

Creating AI Character Videos with ElevenLabs, Midjourney, and Hydra

Copy

Download

Keywords

ElevenLabs Remove

Remove

Voice Design Remove

Remove

Text-to-Speech Remove

Remove

TTS Playground Remove

Remove

Midjourney Remove

Remove

Hydra

Remove

AI video

Remove

lip sync

Remove

character animation Remove

Remove

workflow

Remove

V3

Remove

Copy

Download

Key Takeaways

Design a character voice in ElevenLabs (tone, texture, accent) before generating longer lines in the TTS playground.
Create a character image in Midjourney and use editing/zoom-out (scale out) features to make it suitable for framing and lip sync.
In Hydra, upload the Midjourney image and the ElevenLabs audio to generate an animated, lip-synced video.
The overall pipeline can be completed in roughly 10 minutes for a convincing result.
Prioritize audio quality and performance—"the source is always in the audio."

Copy

Download

Sentiments

Positive: The speakers express excitement and amazement at how quickly high-quality voice, visuals, and animation can be produced, using phrases like 'almost a miracle,' 'I'm blown away,' and highlighting impressive results.

Copy

Download

Enter your query

{{ secondsToHumanTime(time) }}

Back

Forward

{{ Math.round(speed * 100) / 100 }}x

{{ secondsToHumanTime(duration) }}

Select Audio file