Artificial intelligence · 2025
Veo 3 with native audio
Video generation with synchronised dialogue, sound effects and music.
Announced at Google I/O on May 20, 2025, Veo 3 generated video and matching audio together, including lip-synced speech. It ended the silent film era of AI video. OpenAI's Sora 2 followed in September 2025 with audio of its own.
What it built on 1
Watch
Related measurements
The dashed line marks when it first worked.
Training compute of notable AI models Source: Epoch AI, Notable AI Models (CC BY 4.0)
ML hardware FLOP/s per dollar Source: Epoch AI, ML hardware (CC BY 4.0)