Post Thumbnail

Firefly has learned to sense voice and create video

Adobe has released a major update to its Firefly platform. And it’s the only solution truly capable of competing with Google Veo 3. While other developers are trying to catch up with the leaders, Adobe offers unique tools.

The main innovation is the Generate Sound Effects feature. Now you can create sound effects just by describing them in text or even using your own voice. Need thunder or the rustling of leaves? Just tell the system what you need.

The key advantage over Google is that the audio track is created as a separate file. In Veo 3, the sound is tightly bound to the video, and if changes are needed, you have to start from scratch. Adobe allows detailed customization, editing, and synchronization of sound with what’s happening on screen.

A particularly interesting feature is voice-based control of sound. Firefly analyzes the energy and rhythm of your speech to place effects precisely where they’re needed in the video.

The technical side has also been improved. The updated Firefly Video model now produces more natural motion with smooth transitions, especially excelling at dynamic landscapes and animation.

Another important feature is Text to Avatar. Upload a text, choose a virtual character, set the background and emphasis – the system will automatically generate a video. It’s a great solution for educational content and presentations.

Autor: AIvengo
For 5 years I have been working with machine learning and artificial intelligence. And this field never ceases to amaze, inspire and interest me.
Latest News
XPeng introduced world's first female humanoid robot

Chinese electric car manufacturer XPeng introduced the new generation humanoid robot IRON. And this is the first female humanoid!

Michael Burry bet 1.1 billion dollars against Nvidia and Palantir

Michael Burry - this is a legendary investor who predicted the 2008 mortgage crisis. And now he's making a loud move again. Michael bet 1.1 billion dollars in put options against 2 major companies from the AI sector. These are Nvidia and Palantir.

Anthropic conducts interviews with models before sending to retirement

Anthropic published a policy for "decommissioning" outdated AI versions. Key commitment is to preserve weights of all public and actively used internal models for at least the company's lifetime. So that in the future access can be restored if necessary.

Nvidia head believes there is no AI bubble

Nvidia founder Jensen Huang dispelled concerns about a bubble in the AI market. And according to him, the company's latest chips are expected to bring 0.5 trillion dollars in revenue.

Sam Altman is tired of money questions

Sam Altman is tired of questions about OpenAI's money. And this became obvious during a joint interview with Satya Nadella on the Bg2 podcast.