Captions

Mirage is LIVE Generate energetic, high-converting ads with people that don’t exist — complete with animated body language and micro-expressions — using Mirage, the first foundation model built to generate UGC-style content. Get started with a script or an audio file, then specify the look of your spokesperson, their background, outfit, objects, and even emotion. It’s never been easier to iterate and scale ad production with Mirage, now available in Captions Ad Studio.

New week, new partnership drop! Udio is now officially available in Captions. Instantly generate any soundtrack for your video with just a text prompt.

Our UGC video foundation model "Mirage" is available now for marketers everywhere. If you’re spending 30K+ a month or more on ads, you can 10X your outputs at a fraction of the cost.

We’re heading to Las Vegas for?#AdobeSummit next week. If you’re attending, drop by Booth 278D—we’d love to chat!

Eleven Labs ?? Captions

This week, we're excited to announce our partnership with ElevenLabs — making it easier than ever to create videos with studio-grade voices, in any language, directly in Captions. With this partnership, you can dub your videos into different languages, select a professional-quality voice to narrate your content, or clone your voice so you can create polished videos any time, anywhere. Try it out and stay tuned for a third partnership announcement next week!

?? ?? ?? ?? Captions has partnered with the leading gen-AI companies to bring their models into our suite of AI video editing tools. Today, we're announcing the availability of Luma AI's image model, Photon. Marketers, creators, and everyone can now incorporate Photon's incredible image generation capabilities right inside their Captions' projects. ?? We'll continue announce the additional partners over the next couple weeks so stay tuned ?? ...and if you're interested in partnering with Captions, make sure to reach out directly to me or Sam Halstead!

At Captions, we're not using AI to replace humans, we're using it to transform the craft of video creation and editing. We've partnered with 15 foundation model companies that are leading this transformation in domains like images, videos, voice, music and more. You'll be able to access the latest models from these industry leading companies right within Captions for seamless video creation. First up we're announcing image generation with Luma AI Photon. Stay tuned for more!

We’ve partnered with fifteen generative AI companies to bring their latest models to Captions. This means you can now seamlessly incorporate generated elements from your favorite models across image, voice, music, and video — all within our video editor. In the next few weeks, we'll be announcing our partners across each category. First up? Luma AI. Create images with Luma AI’s Photon model, now on Captions and available on iOS and web.

The AI lip sync era is over: our team at Captions is excited to usher in a new era of audio-to-video foundation models. Captions was among the first to commercialize lip sync models, launching the original "lipdub" and "AI dubbing" in 2022. We trained our models and worked with companies like synclabs (pre-YC) as early as 2022. These models gained massive popularity and are used today by companies like Captions, Heygen and Synthesia for everything from dubbing to AI avatars. As the AI lip sync use cases have grown, a key weakness has emerged — half of visual communication happens through facial expressions and body language, not just lip movement. We've all seen it: AI lip sync videos saying one thing with their lips, but their expressions or body language saying another. This is the definition of bad acting. Enter Mirage by Captions, the world's first audio-to-video foundation model. Mirage uses audio alone as an input to generate realistic talking video at 720p resolution — all with "people" who don't exist. Optionally, you can prompt with text for changing location, clothes, accessories, and more. Today, we're releasing an early preview of Mirage to show that audio is enough to drive full-body animation, facial expression, eye movement, and more. To underscore an important point: We recognize this an incredibly useful foundation model, but one that can be dangerous if used incorrectly or maliciously. We are carefully crafting the surface areas where Mirage will be available to consumers in a safe way, and access will be limited as we release this technology. Mirage will be released within Captions suite of AI video editing and production tools over the coming weeks. Please apply below for access.