FLUX 3 Video opens on OpenRouter, with native synced audio
- Source
- x.com
- Date
FLUX 3 Video from @bfl_ai is now available for everyone on OpenRouter. One unified multimodal model family for video, audio, image, and action-prediction. Serious, fun, creative, real, cinematic, whatever you need it to be. Jointly trained in one unified architecture.
FLUX 3 adds real-world grounding, diverse styles, multilingual dialogue, and agentic chaining. It can extend any video and carry momentum, framing, and scene logic forward. https://t.co/z50EUI7uh4
Text to video, image to video with multiple key frames, video continuation, and native audio with lipsync, effects, and ambience. Access all advanced capabilities of FLUX 3 through OpenRouter's Video API. https://t.co/l9UzyOyWKy
Context
Black Forest Labs' FLUX 3 Video creates sound alongside moving images, including dialogue, effects and ambience. Its continuation mode takes up to four seconds of existing video and audio as for what happens next. The intended benefit is continuity across a clip boundary: both the movement and the sound inform the extension. The developer describes this mechanism in its August 4 release article.
OpenRouter's announcement makes these generation and continuation capabilities accessible through its Video API. That gives developers a common interface for creating a scene with sound and extending existing footage.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Checking sign-in…
Loading comments…