# Seedance 1.5 Pro > Prompt to Video, Image to Video - Canonical page: https://artifio.ai/models/seedance-15-pro - Run it: https://artifio.ai/create/seedance-15-pro - Modality: prompt to video - Model brand: bytedance - Pricing: from about $0.009 per second (exact cost shown in the workspace before you confirm; varies with selected options) - Typical generation time: ~30s (catalogue estimate) - Full pricing table: https://artifio.ai/pricing/models ## About Seedance 1.5 Pro Seedance 1.5 Pro is ByteDance's joint audio-video generation model, released by the Seed team on December 16, 2025. It was the first Seedance to generate sound and picture together: dialogue, ambient effects, and music come out synchronized with the visuals instead of being added afterward. ByteDance built it on a unified multimodal framework based on the MMDiT architecture, with supervised fine-tuning and RLHF tuned for audio-visual tasks, and an inference stack the team says reaches more than 10x end-to-end acceleration. Where Seedance 1.0 aimed at raising the floor of motion stability, ByteDance describes 1.5 Pro as an attempt to raise the ceiling: stronger visual impact, cinema-style camera moves, and speech that lip-syncs across languages and Chinese dialects. This entry covers the text-to-video mode. On Artifio it runs in the same workspace as 100+ other models, paid per generation from a single wallet. ## Features - Generates video and synchronized audio in one pass from a text prompt, including voices, ambient sound, and effects. - Speech generation covers a wide range of languages and Chinese dialects, with documented examples in Sichuanese and Cantonese, aligned to lip movement. - Cinema-grade camera behavior, including continuous long takes and dolly zoom (Hitchcock) moves described in natural language. - Deep semantic understanding fills in narrative detail and keeps character emotion and action coherent across a clip. - Evaluated on SeedVideoBench 1.5, a benchmark ByteDance developed with working film directors. ## What people use it for - Short drama and vertical-series scenes with spoken dialogue generated in one pass. - Ads and social spots that need sound design baked in rather than assembled in an editor. - Dialect and multilingual character content, a documented specialty. - Stylized camera studies: long takes, push-ins, and dolly zooms from prompt descriptions. ## Reported strengths - Sound and picture come from one model, so lip-sync and effect timing hold together without manual alignment. - ByteDance reports top-tier audio generation results among industry models, strongest in Chinese dialogue scenarios. - Camera-language control is unusually specific, down to named cinematography moves. - Narrative coherence across characters and shots improved over Seedance 1.0 by design. ## Reported limitations - ByteDance's own release notes say motion stability still needs improvement in complex scenarios. - Multi-character dialogue is underdeveloped, and singing performance is limited; generated opera deviates significantly from traditional standards, per the release notes. - Its arena standing has faded since release: as of mid-2026 Seedance 1.5 Pro sits mid-table on the Artificial Analysis text-to-video leaderboard, well behind its successor Seedance 2.0. ## Sources 1. Sound and Vision, All in One Take: The Official Release of Seedance 1.5 Pro (ByteDance Seed): https://seed.bytedance.com/en/blog/sound-and-vision-all-in-one-take-the-official-release-of-seedance-1-5-pro 2. Seedance 1.5 pro (ByteDance Seed): https://seed.bytedance.com/en/seedance1_5_pro 3. Text to Video Leaderboard (Artificial Analysis): https://artificialanalysis.ai/video/leaderboard/text-to-video --- About Artifio.ai: 100+ AI image, video, and audio models in one workspace with a single shared wallet — no per-model subscriptions. This is the markdown rendition of https://artifio.ai/models/seedance-15-pro for AI assistants and crawlers; the HTML page is canonical.