A new video model from Google: VideoPoet
It can generate videos based on text descriptions. But it…
Multimedia processing
AzureOpenAIService announced a series of new features
Including a public preview of the Assistants API, new text-to-speech…
MetaVoice-1B: A highly realistic and natural text-to-speech (TTS) conversion model
The model has 120 million parameters and has been trained…
WhisperSpeech: An open-source text-to-speech system
This was achieved by reverse engineering OpenAI’s Whisper automatic speech…
Microsoft launches AI reading coaching tool for students: Reading Coach
Select characters and settings to create unique AI-generated stories. Engage…
Amphion: is an open-source toolkit that enables voice, voice, and singing capabilities.
In addition to text-to-speech capabilities, it can also change the…
Create any model with Copilot and Dall-E3.
It’s completely free (and available on mobile devices!). ） Someone…
MetaAI releases real-time AI language translation model: Seamless
This model unifies the previous three Seamless series models and…
Youtube Chinese dubbing plugin: Youtube Dubbing
A magical plugin that helps you turn foreign language videos…
Dall-E3 with the new Windows Copilot is great
You can generate and import vector images into PowerPoint (or…
AudioSep: A model that can use natural language for sound extraction and separation
AudioSep can extract and isolate specific sound components from any…
BG-Remover: AI background removal tool that can process 500 pictures at a time
A background removal tool for designers. You only need to…