Beat API

Overview

Beat API's AI Music Video API is a workflow API that creates asynchronous music video tasks from audio URLs, visual references, lyrics, and prompt direction. Requests accept audio, images, lyrics or SRT, prompt direction, lip-sync options, aspect ratio, resolution, quality, and compose mode through a single task contract. Standard generation supports 10–180s and Premium supports 10–300s, with per-second pricing ranging from $0.08 to $0.36 per second depending on mode, quality, and resolution. Generation runs as an async task layer: assets are submitted once, a task id is returned, and the run moves through queued, processing, succeeded, or failed states. Supported tasks return an ordered storyboard with stable shot IDs, status, duration, prompt, lyric text, and hosted media metadata. Individual shots can be revised without restarting the full music-video task, and selected shot IDs can be composed into a new MP4 while preserving the original task and its operation history. Billing is charged in USD from server-detected audio duration before processing begins, and refunded for eligible failures. Hosted MP4 output, polling, webhooks, task logs, and uploaded asset handling are included. The page is written for developers building creator tools, music apps, campaign builders, lyric video API flows, and automation systems that need repeatable audio-to-video generation behind an API.