Also elevenlabs, voice is called "Myrddin" in the voice library
@aibreakfast
-
Midjourney Video Sound Tip: Use Elevenlabs for Custom Sound Effects
By
–
Pro tip for sound if you're messing around with Midjourney Video:
— AI Breakfast (@AiBreakfast) 23 juin 2025
You can use Elevenlabs to generate any sound effect via prompting. Each one ends up being pennies. Most of these sounds fx were one-shot
Way more fun than leaving sound to the video generator imo (like in Veo 3) pic.twitter.com/7oVRuzyOsBPro tip for sound if you're messing around with Midjourney Video: You can use Elevenlabs to generate any sound effect via prompting. Each one ends up being pennies. Most of these sounds fx were one-shot Way more fun than leaving sound to the video generator imo (like in Veo 3)
-
Embodied Web Agents: Bridging Physical-Digital Realms for Real-World Tasks
By
–
https://t.co/63LYHHBiEV pic.twitter.com/fNffHwnsN0
— AI Breakfast (@AiBreakfast) 20 juin 2025Meet Embodied Web Agents that bridge physical-digital realms. Imagine embodied agents that can search for online recipes, shop for ingredients and cook for you. Embodied web agents search internet information for implementing real-world embodied tasks. All data, codes and web
-
AI Tools for Creating Engaging History Videos on YouTube
By
–
Anyone with an ounce of creativity could quit their job and just use midjourney video to create cool history videos on YouTube. -ChatGPT/Grok for ideas and script
-Midjourney for images -> video clips
-Suno for backtracking music
-CapCut for editing
-ElevenLabs for voiceover -
Faster, cheaper AI image generation, integrates with Midjourney
By
–
Much faster generation and way cheaper than Veo 3. Plus being able to start with an image you made in Midjourney is
-
Midjourney Video reaches an impressive new level
By
–
Midjourney Video is on another level. pic.twitter.com/vCAQB8ZTQo
— AI Breakfast (@AiBreakfast) 19 juin 2025Midjourney is on another level.
-
Director.AI: Free Web Automation Like OpenAI’s Operator
By
–
This is basically OpenAI's Operator, but free.https://t.co/qks1kdg7Uf by Browserbase.
— AI Breakfast (@AiBreakfast) 19 juin 2025
Describe tasks in plain english and it runs through the web clicking around, finding answers, and collecting data.
Soon there will be no limit to these things. pic.twitter.com/EMt7zNCG86This is basically OpenAI's Operator, but free. http://
Director.AI by Browserbase. Describe tasks in plain english and it runs through the web clicking around, finding answers, and collecting data. Soon there will be no limit to these things. -
OpenAI podcast: GPT-5 likely release this summer
By
–
"GPT-5 probably sometime this summer." From latest OpenAI podcast:
-
AI image generators’ realism is distracting, focus on imperfections.
By
–
Midjourney and Google Flow produce great high-realism, but it's too distracting because your eye is constantly hunting for imperfections. pic.twitter.com/tZm90juv8F
— AI Breakfast (@AiBreakfast) 18 juin 2025Midjourney and Google Flow produce great high-realism, but it's too distracting because your eye is constantly hunting for imperfections.
-
Magnific AI preserves structure; Kling animates speaking in 10 minutes
By
–
Of course you could generate a color version in ChatGPT, but Magnific AI does a great job at keeping the "structure" of an old image and overlaying a new style on top of it. Kling took 2-3 renditions before the speaking part made sense. But still this all took 10 minutes max.