Speech in Flow

Add AI-generated speech to videos from a single image

Visit Speech in Flow →

Speech in Flow is an experimental feature within Google's AI filmmaking tool, Flow, powered by the Veo 3 model. It enables users to generate videos from a single starting image and add custom AI-generated dialogue or speech to those videos. It is aimed at creators and filmmakers looking to animate still images with realistic AI-generated audio.

At a glance

Company
Google
Pricing
unknown
API available
No
Self-hostable
No
Launched
2025-07
Last verified
2026-05-11

Capabilities

text-to-speechimage-to-videoai-dialogue-generationspeech-synthesisvideo-generation

Categories

Alternatives

For AI agents: machine-readable markdown version of this page at /tools/speech-in-flow.md, or send Accept: text/markdown.