Limited-time offer: 20% off PixVerse V6 Max. Ends November 30. Try in Playground
Browse our latest posts to learn more about us and what our platform has to offer.
API Access
Seedance 2.5 Draft Mode on EmpirioLabs: try a shot as a 480p draft, then render the one you pick at 1080p or in native 4K from the same prompt, references and seed.
Seedance 2.5 now renders native 4K on EmpirioLabs: 3840x2160 clips of up to 30 seconds with native audio, and Draft Mode can render your pick in 4K.
Qwen4 Max is Alibaba's next-generation Qwen flagship for coding, frontend design, office work, and complex agents, with image and video understanding, a 1M token context, adjustable reasoning effort, and five built-in tools.
Seedance 2.5 Flash is available on EmpirioLabs: clips of up to 30 seconds at 480p or 720p, with native audio, up to 20 image, video and audio references, editing and extension.
Seedream 5.5 is available on EmpirioLabs: text-to-image and edits with up to 10 reference images, native transparent images, and layer decomposition into up to 99 layers with text recognition.
Kimi K3.1 Pro is available on EmpirioLabs: Moonshot's flagship reasoning model for long coding and agent work, with a 1M token context, image input, and web search.
Kling 4.0 Flash is available on EmpirioLabs: the faster, lower-cost Kling 4.0, with 3 to 20 second video at 720p and native audio from text, a first frame, reference images and videos, or a video to edit.
MiniMax H3 Lite is available on EmpirioLabs: lower-cost video of 4 to 15 seconds at 480p or 768p with native stereo audio, from text, a first and last frame, or image, video, and audio references.
MiniMax H3 Highspeed is available on EmpirioLabs: fast 768p video of 4 to 15 seconds with native stereo audio, from text, a first and last frame, or image, video, and audio references.
Kling 4.0 is available on EmpirioLabs: 3 to 30 second video at 720p or 1080p with native audio, from text, keyframes, reference images and videos, or a video to edit.
Qwen Audio 3.1 TTS Plus is available on EmpirioLabs: the quality tier of Qwen Audio 3.1 speech synthesis, with 4 multilingual voices, plain-language delivery direction, inline tags, and voice cloning.
Qwen Audio 3.1 Realtime Flash is a voice conversation model you talk to over a WebSocket, with 88 voices, 14 languages, and web search that works in the same session as your own functions.
Showing 1–12 of 71 articles
Explore our models, or contact us about business inquiries, custom deployments, or anything else.