Speech in Flow
Bring your images to life with speech
Visit website →About
Speech in Flow is an experimental feature in Flow, Google's AI filmmaking tool. Powered by the Veo 3 model, it adds custom AI-generated spoken dialogue to videos created from a single starting image, so a still picture can become an animated scene with characters that talk.
It removes the need to record or edit audio separately when building short narrative clips from images.
It is aimed at filmmakers, storytellers, and creators using Flow who want to bring images to life with dialogue as part of an AI-assisted production workflow, rather than adding voice in a separate step.
AI-assisted draft, human-reviewed before publishing — see how we choose & review tools.
Why we picked it
Speech in Flow fills a specific gap in image-to-video tools — adding AI-generated dialogue to a scene built from a single still image, so a character talks without ever recording or editing audio separately.
Related tools
- 1 SupoClip Turn long videos into viral shorts with an open-source AI clipper Freemium
- 2 ngram Turn text into polished videos for your team Freemium
- 3 OpenScreen Free open-source screen recorder with AI editing and auto-zooms Free
- 4 Runway AI video generation and editing studio, billed in US dollars Freemium
- 5 Refs A film library that helps Claude make better videos Freemium
- 6 Pexo AI video agent that turns your idea into a publish-ready video Freemium