✨TUTORIAL✨ Runway's Generative Audio tool gives you more options: • Text-to-voice or voice cloning • Animate & lip sync static images • Add audio & lip sync effects to videos Upload audio files, generate with a preset voice, or record audio through the mic: @runwayml [img:vid-ZwZzhVMlP]

How to make a Lip Sync video: Go to Generative Audio > Text to Speech tool on Runway Get your audio ready by uploading an existing file, recording a new clip, or generating text-to-speech audio Upload or select the image/video of the face you want to animate Click Generate: [img:vid-eKxm1RxrP]

Tips for images and videos used with Lip Sync: Images: The face should be front-facing, framed from the shoulders up, and photorealistic in style for best results. Video input: Videos with minimal mouth/camera/body movement and lighting changes seem to work better. [img:vid-AyNrO5ygH]

I tested the Lip Sync feature with preset voices, my cloned voice, and my uploaded voice. I prefer the output with my uploaded voice recordings, like this still image example: [img:vid-p4Q_T2vkC]

The preset voices work well with text-to-voice. I appreciate the way Runway adjusts the lip synced video output length and style to match the length of the audio. Watch the original video clip on the left, compared to the output with lip sync on the right: [img:vid-G9Qt0UGJ6]

Overall, this feature adds to our toolkit to tell better stories with visuals: [img:vid-Vyspei9f7]

Thanks for reading. Follow @HBCoop_ to learn about interesting generative AI tools and tips from a different perspective. Repost the 1st post below to share this thread:twitter.com/HBCoop_/status/1769487670110023718