Grok now supports text-to-video generation, one sentence can generate a video with sound effects
Grok Imagine, under xAI, has achieved short video generation from pure text. Users can obtain a 6-15 second video with sound effects, dynamic shots, and professional quality within 17 seconds by inputting a description, without needing image input or editing skills. This upgrade connects the idea to the final product, challenging the market position of OpenAI Sora and Google Veo with its high-speed advantage.