146
Turn text, photos, clips, or audio into 4–15 second videos with Seedance 2.0. This powerful API offers four variants: standard, fast, face, and fast-face, catering to diverse needs from general use to real-person animation.
Versatile Input: Accepts text prompts, image URLs, video clips, and audio files to generate dynamic video content.
High-Quality Output: Supports resolutions up to 4K, with options for generated audio and lip-sync capabilities when using face variants.
Flexible Pricing: Features per-second credit-based pricing, making it cost-effective for various project scales. 1 credit equals $0.001 USD.
Efficient Workflow: Utilizes an asynchronous, OpenAI-style endpoint for seamless integration and task management.
Continuous Chaining: The return_last_frame option allows for chaining multiple video generations to create longer, continuous outputs without prompt drift.
Real-Person Animation: Face variants enable lip-syncing with provided audio and reference images or videos, ideal for character animation and explainers.
Cost Estimation: An integrated estimator helps calculate costs based on chosen parameters before generation.
Key Features:
Four Variants: Choose between standard, fast, face, and fast-face for optimized performance and features.
Resolution Options: Generate videos in 480p, 720p, 1080p, and 4K.
Audio Generation: Option to synthesize audio tracks to accompany the video content.
Reference-Driven Generation: Utilize reference images, videos, and audio for precise control over output style and motion.
NSFW Filter: An optional NSFW filter is available for content moderation.
Seedance 2.0 is designed for developers and creators looking to efficiently produce high-quality video content from various inputs, streamlining the video creation process.
Built with